diff --git a/pywb/binsearch.py b/pywb/binsearch.py index ef3171f1..2027e204 100644 --- a/pywb/binsearch.py +++ b/pywb/binsearch.py @@ -5,6 +5,7 @@ import itertools class FileReader: def __init__(self, filename): self.fh = open(filename, 'rb') + self.filename = filename self.size = os.path.getsize(filename) def getsize(self): @@ -16,6 +17,9 @@ class FileReader: def seek(self, offset): return self.fh.seek(offset) + def close(self): + return self.fh.close() + def binsearch_offset(reader, key, compare_func = cmp, block_size = 8192): min = 0 @@ -65,28 +69,79 @@ def search(reader, key, prev_size = 0, compare_func = cmp, block_size = 8192): def gen_iter(line): if prev_size == 1: - yield prev + yield prev.rstrip() elif prev_size > 1: for i in prev_deque: - yield i + yield i.rstrip() while line: - yield line + yield line.rstrip() line = reader.readline() return gen_iter(line) -# Iterate over exact matches -def iter_exact(reader, key): +# Iterate over prefix matches +def iter_prefix(reader, key): + """ + >>> print_test_cdx('org,iana)/domains/root', iter_prefix) + org,iana)/domains/root 20140126200912 http://www.iana.org/domains/root text/html 200 YWA2R6UVWCYNHBZJKBTPYPZ5CJWKGGUX - - 2691 657746 iana.warc.gz + org,iana)/domains/root/db 20140126200927 http://www.iana.org/domains/root/db/ text/html 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 446 671278 iana.warc.gz + org,iana)/domains/root/db 20140126200928 http://www.iana.org/domains/root/db text/html 200 DHXA725IW5VJJFRTWBQT6BEZKRE7H57S - - 18365 672225 iana.warc.gz + org,iana)/domains/root/servers 20140126201227 http://www.iana.org/domains/root/servers text/html 200 AFW34N3S4NK2RJ6QWMVPB5E2AIUETAHU - - 3137 733840 iana.warc.gz + """ + lines = search(reader, key) - for x in lines: - if not x.startswith(key): - break - - yield x + return itertools.takewhile(lambda line: line.startswith(key), lines) +def iter_exact(reader, key, tok = ' '): + """ + >>> print_test_cdx('org,iana)/domains/root', iter_exact) + org,iana)/domains/root 20140126200912 http://www.iana.org/domains/root text/html 200 YWA2R6UVWCYNHBZJKBTPYPZ5CJWKGGUX - - 2691 657746 iana.warc.gz + + >>> print_test_cdx('org,iana)/', iter_exact) + org,iana)/ 20140126200624 http://www.iana.org/ text/html 200 OSSAPWJ23L56IYVRW3GFEAR4MCJMGPTB - - 2258 334 iana.warc.gz + + >>> print_test_cdx('org,iana)/domains/root/db', iter_exact) + org,iana)/domains/root/db 20140126200927 http://www.iana.org/domains/root/db/ text/html 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 446 671278 iana.warc.gz + org,iana)/domains/root/db 20140126200928 http://www.iana.org/domains/root/db text/html 200 DHXA725IW5VJJFRTWBQT6BEZKRE7H57S - - 18365 672225 iana.warc.gz + + >>> print_test_cdx('org,iaana)/', iter_exact) + >>> print_test_cdx('org,ibna)/', iter_exact) + + >>> print_test_cdx('org,iana)/time-zones', iter_exact) + org,iana)/time-zones 20140126200737 http://www.iana.org/time-zones text/html 200 4Z27MYWOSXY2XDRAJRW7WRMT56LXDD4R - - 2449 569675 iana.warc.gz + """ + + lines = search(reader, key) + + def check_key(line): + line_key = line.split(tok, 1)[0] + return line_key == key + + return itertools.takewhile(check_key, lines) + + +import utils +if __name__ == "__main__" or utils.enable_doctests(): + + def create_test_cdx(test_file): + path = os.path.dirname(os.path.realpath(__file__)) + '/../test/' + test_file + return FileReader(path) + + test_cdx = create_test_cdx('iana.cdx') + + def print_test_cdx(key, iter_func, filename = None): + cdx = test_cdx if not filename else create_test_cdx(filename) + for line in iter_func(cdx, key): + print line + + #cdx.close() + + import doctest + doctest.testmod() + diff --git a/pywb/cdxserve.py b/pywb/cdxserve.py new file mode 100644 index 00000000..e70e3369 --- /dev/null +++ b/pywb/cdxserve.py @@ -0,0 +1,328 @@ +import binsearch +import indexreader +import bisect +import itertools +import re + +from heapq import merge +from collections import deque + +class LocalCDXServer: + def __init__(sources): + self.sources = sources + + pass + + +def merge_sort_streams(sources, key, iter_func): + """ + >>> test_cdx(key = 'org,iana)/', sources = ['dupes.cdx', 'iana.cdx']) + org,iana)/ 20140126200624 http://www.iana.org/ text/html 200 OSSAPWJ23L56IYVRW3GFEAR4MCJMGPTB - - 2258 334 iana.warc.gz + org,iana)/ 20140127171238 http://iana.org unk 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 343 1858 dupes.warc.gz + org,iana)/ 20140127171238 http://www.iana.org/ warc/revisit - OSSAPWJ23L56IYVRW3GFEAR4MCJMGPTB - - 536 2678 dupes.warc.gz + """ + + def load_src(source): + source = binsearch.FileReader(source) + source = iter_func(source, key) + return source + + # Optimize: no need to merge if just one input + if len(sources) == 1: + return load_src(sources[0]) + + source_iters = map(load_src, sources) + merged_stream = merge(*(source_iters)) + return merged_stream + +#================================================================= +# convert text cdx stream to CDXCaptureResult +def make_cdx_iter(text_iter): + return itertools.imap(lambda line: indexreader.CDXCaptureResult(line), text_iter) + + +#================================================================= +# limit cdx to at most limit +def cdx_limit(cdx_iter, limit): + """ + >>> test_cdx('org,iana)/_css/2013.1/fonts/opensans-bold.ttf', limit = 3) + org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200625 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf application/octet-stream 200 YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 117166 198285 iana.warc.gz + org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200654 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 548 482544 iana.warc.gz + org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200706 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 552 495230 iana.warc.gz + + """ + + for cdx, _ in itertools.izip(cdx_iter, xrange(limit)): + yield cdx + + +#================================================================= +# reverse cdx +def cdx_reverse(cdx_iter, limit): + """ + >>> test_cdx('org,iana)/_css/2013.1/fonts/opensans-bold.ttf', reverse = True, resolve_revisits = True, limit = 3) + org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126201308 https://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf application/octet-stream 200 YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 551 783712 iana.warc.gz 117166 198285 iana.warc.gz + org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126201249 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf application/octet-stream 200 YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 552 771773 iana.warc.gz 117166 198285 iana.warc.gz + org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126201240 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf application/octet-stream 200 YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 551 757988 iana.warc.gz 117166 198285 iana.warc.gz + + >>> test_cdx('org,iana)/_js/2013.1/jquery.js', reverse = True, resolve_revisits = True, limit = 1) + org,iana)/_js/2013.1/jquery.js 20140126201307 https://www.iana.org/_js/2013.1/jquery.js application/x-javascript 200 AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 543 778507 iana.warc.gz 33449 7311 iana.warc.gz + """ + + # optimize for single last + if limit == 1: + last = None + + for cdx in cdx_iter: + last = cdx + + return [last] + + reverse_cdxs = deque(maxlen = limit) + + for cdx in cdx_iter: + reverse_cdxs.appendleft(cdx) + + return reverse_cdxs + + + #================================================================= +# filter cdx by regex if each filter is field:regex form, +# apply filter to cdx[field] +def cdx_filter(cdx_iter, filter_strings): + """ + >>> test_cdx(key = 'org,iana)/domains', match_func = binsearch.iter_prefix, filters = ['mimetype:text/html']) + org,iana)/domains 20140126200825 http://www.iana.org/domains text/html 200 7UPSCLNWNZP33LGW6OJGSF2Y4CDG4ES7 - - 2912 610534 iana.warc.gz + org,iana)/domains/arpa 20140126201248 http://www.iana.org/domains/arpa text/html 200 QOFZZRN6JIKAL2JRL6ZC2VVG42SPKGHT - - 2939 759039 iana.warc.gz + org,iana)/domains/idn-tables 20140126201127 http://www.iana.org/domains/idn-tables text/html 200 HNCUFTJMOQOGAEY6T56KVC3T7TVLKGEW - - 8118 715878 iana.warc.gz + org,iana)/domains/int 20140126201239 http://www.iana.org/domains/int text/html 200 X32BBNNORV4SPEHTQF5KI5NFHSKTZK6Q - - 2482 746788 iana.warc.gz + org,iana)/domains/reserved 20140126201054 http://www.iana.org/domains/reserved text/html 200 R5AAEQX5XY5X5DG66B23ODN5DUBWRA27 - - 3573 701457 iana.warc.gz + org,iana)/domains/root 20140126200912 http://www.iana.org/domains/root text/html 200 YWA2R6UVWCYNHBZJKBTPYPZ5CJWKGGUX - - 2691 657746 iana.warc.gz + org,iana)/domains/root/db 20140126200927 http://www.iana.org/domains/root/db/ text/html 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 446 671278 iana.warc.gz + org,iana)/domains/root/db 20140126200928 http://www.iana.org/domains/root/db text/html 200 DHXA725IW5VJJFRTWBQT6BEZKRE7H57S - - 18365 672225 iana.warc.gz + org,iana)/domains/root/servers 20140126201227 http://www.iana.org/domains/root/servers text/html 200 AFW34N3S4NK2RJ6QWMVPB5E2AIUETAHU - - 3137 733840 iana.warc.gz + """ + + filters = [] + + class Filter: + def __init__(self, string): + # invert filter + self.invert = string.startswith('!') + if self.invert: + string = string[1:] + + parts = string.split(':', 1) + # no field set, apply filter to entire cdx + if len(parts) == 1: + self.field = '' + else: + # apply filter to cdx[field] + self.field = parts[0] + string = parts[1] + + self.regex = re.compile(string) + + def __call__(self, cdx): + val = cdx[self.field] if self.field else str(cdx) + matched = self.regex.match(val) is not None + return matched ^ self.invert + + filters = map(Filter, filter_strings) + + for cdx in cdx_iter: + if all (x(cdx) for x in filters): + yield cdx + + + +#================================================================= +# sort cdx by closest to timestamp +def cdx_collapse_time(cdx_iter, timelen = 10): + """ + >>> test_cdx(key = 'org,iana)/_css/2013.1/screen.css', collapse_time = 11) + org,iana)/_css/2013.1/screen.css 20140126200625 http://www.iana.org/_css/2013.1/screen.css text/css 200 BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 8754 41238 iana.warc.gz + org,iana)/_css/2013.1/screen.css 20140126201054 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 543 706476 iana.warc.gz + + + >>> test_cdx(key = 'org,iana)/_css/2013.1/screen.css', collapse_time = 11, resolve_revisits = True) + org,iana)/_css/2013.1/screen.css 20140126200625 http://www.iana.org/_css/2013.1/screen.css text/css 200 BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 8754 41238 iana.warc.gz - - - + org,iana)/_css/2013.1/screen.css 20140126201054 http://www.iana.org/_css/2013.1/screen.css text/css 200 BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 543 706476 iana.warc.gz 8754 41238 iana.warc.gz + + """ + + last_dedup_time = None + + for cdx in cdx_iter: + curr_dedup_time = cdx['timestamp'][:timelen] + + # yield if last_dedup_time is diff, otherwise skip + if curr_dedup_time != last_dedup_time: + last_dedup_time = curr_dedup_time + yield cdx + + + +#================================================================= +# sort CDXCaptureResult by closest to timestamp +def cdx_sort_closest(closest, cdx_iter, limit = 10): + """ + >>> test_cdx(closest_to = '20140126200826', key = 'org,iana)/_css/2013.1/fonts/opensans-bold.ttf', timestamp_only = True) + 20140126200826 + 20140126200816 + 20140126200805 + 20140126200912 + 20140126200738 + 20140126200930 + 20140126200718 + 20140126200706 + 20140126200654 + 20140126200625 + + # equal dist prefer earlier + >>> test_cdx(closest_to = '20140126200700', key = 'org,iana)/_css/2013.1/fonts/opensans-bold.ttf', resolve_revisits = True, timestamp_only = False, limit = 2) + org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200654 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf application/octet-stream 200 YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 548 482544 iana.warc.gz 117166 198285 iana.warc.gz + org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200706 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf application/octet-stream 200 YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 552 495230 iana.warc.gz 117166 198285 iana.warc.gz + + >>> test_cdx(closest_to = '20140126200659', key = 'org,iana)/_css/2013.1/fonts/opensans-bold.ttf', resolve_revisits = True, timestamp_only = True, limit = 2) + 20140126200654 + 20140126200706 + + >>> test_cdx(closest_to = '20140126200701', key = 'org,iana)/_css/2013.1/fonts/opensans-bold.ttf', resolve_revisits = True, timestamp_only = True, limit = 2) + 20140126200706 + 20140126200654 + + """ + closest_cdx = [] + + closest_sec = utils.timestamp_to_sec(closest) + + for cdx in cdx_iter: + sec = utils.timestamp_to_sec(cdx['timestamp']) + key = abs(closest_sec - sec) + + # create tuple to sort by key + bisect.insort(closest_cdx, (key, cdx)) + + if len(closest_cdx) == limit: + # assuming cdx in ascending order and keys have started increasing + if key > closest_cdx[-1]: + break + + if len(closest_cdx) > limit: + closest_cdx.pop() + + + return itertools.imap(lambda x: x[1], closest_cdx) + + + +#================================================================= +# resolve revisits + +# Fields to append from cdx original to revisit +ORIG_TUPLE = ['length', 'offset', 'filename'] + +def cdx_resolve_revisits(cdx_iter): + """ + >>> test_cdx('org,iana)/_css/2013.1/fonts/inconsolata.otf', resolve_revisits = True) + org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126200826 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf application/octet-stream 200 LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 34054 620049 iana.warc.gz - - - + org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126200912 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf application/octet-stream 200 LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 546 667073 iana.warc.gz 34054 620049 iana.warc.gz + org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126200930 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf application/octet-stream 200 LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 534 697255 iana.warc.gz 34054 620049 iana.warc.gz + org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126201055 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf application/octet-stream 200 LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 547 714833 iana.warc.gz 34054 620049 iana.warc.gz + org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126201249 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf application/octet-stream 200 LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 551 768625 iana.warc.gz 34054 620049 iana.warc.gz + + >>> test_cdx('org,iana)/domains/root/db', resolve_revisits = True) + org,iana)/domains/root/db 20140126200927 http://www.iana.org/domains/root/db/ text/html 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 446 671278 iana.warc.gz - - - + org,iana)/domains/root/db 20140126200928 http://www.iana.org/domains/root/db text/html 200 DHXA725IW5VJJFRTWBQT6BEZKRE7H57S - - 18365 672225 iana.warc.gz - - - + """ + + + originals = {} + + for cdx in cdx_iter: + is_revisit = (cdx['mimetype'] == 'warc/revisit') or (cdx['filename'] == '-') + + digest = cdx['digest'] + + original_cdx = originals.get(digest) + + if not original_cdx and not is_revisit: + originals[digest] = cdx + + + if original_cdx and is_revisit: + fill_orig = lambda field: original_cdx[field] + # Transfer mimetype and statuscode + cdx['mimetype'] = original_cdx['mimetype'] + cdx['statuscode'] = original_cdx['statuscode'] + else: + fill_orig = lambda field: '-' + + # Always add either the original or empty '- - -' + for field in ORIG_TUPLE: + cdx['orig.' + field] = fill_orig(field) + + yield cdx + + + + + +import utils +if __name__ == "__main__" or utils.enable_doctests(): + import os + + test_dir = os.path.dirname(os.path.realpath(__file__)) + '/../test/' + + def create_test_cdx(test_file): + path = os.path.dirname(os.path.realpath(__file__)) + '/../test/' + test_file + return binsearch.FileReader(path) + + def wrap_test_path(filenames): + return map(lambda x: test_dir + x, filenames) + + test_cdx_iter = create_test_cdx('iana.cdx') + + def test_cdx(key, + closest_to = None, + limit = 10, + collapse_time = None, + timestamp_only = False, + resolve_revisits = False, + reverse = False, + filters = None, + sources = ['iana.cdx'], + match_func = binsearch.iter_exact): + + cdx_iter = merge_sort_streams(wrap_test_path(sources), key, match_func) + + cdx_iter = make_cdx_iter(cdx_iter) + + if resolve_revisits: + cdx_iter = cdx_resolve_revisits(cdx_iter) + + if filters: + cdx_iter = cdx_filter(cdx_iter, filters) + + if collapse_time: + cdx_iter = cdx_collapse_time(cdx_iter, collapse_time) + + if reverse: + cdx_iter = cdx_reverse(cdx_iter, limit) + + if closest_to: + cdx_iter = cdx_sort_closest(closest_to, cdx_iter, limit) + + if limit: + cdx_iter = cdx_limit(cdx_iter, limit) + + for cdx in cdx_iter: + print cdx['timestamp'] if timestamp_only else cdx + + + + import doctest + doctest.testmod() + + diff --git a/pywb/indexreader.py b/pywb/indexreader.py index f5b10669..eaef01db 100644 --- a/pywb/indexreader.py +++ b/pywb/indexreader.py @@ -114,10 +114,22 @@ class CDXCaptureResult(OrderedDict): for header, field in itertools.izip(cdxformat, fields): self[header] = field - # setattr(self, header, field) - #def __repr__(self): - # return str(vars(self)) + self.cdxline = cdxline + + def __setitem__(self, key, value): + OrderedDict.__setitem__(self, key, value) + + # force regen on next __str__ call + self.cdxline = None + + + def __str__(self): + if self.cdxline: + return self.cdxline + + li = itertools.imap(lambda (n, val): val, self.items()) + return ' '.join(li) diff --git a/pywb/replay_resolvers.py b/pywb/replay_resolvers.py index c0913c2c..11c59a60 100644 --- a/pywb/replay_resolvers.py +++ b/pywb/replay_resolvers.py @@ -7,6 +7,7 @@ def PrefixResolver(prefix, contains = ''): def makeUrl(url): return [prefix + url] if (contains in url) else [] + print "prefix: " + prefix + " contains: " + contains return makeUrl #====================================== @@ -30,13 +31,13 @@ class PathIndexResolver: self.reader = binsearch.FileReader(pathindex_file) def __call__(self, filename): - result = binsearch.iter_exact(self.reader, filename) + result = binsearch.iter_exact(self.reader, filename, '\t') def gen_list(result): for pathline in result: path = pathline.split('\t') if len(path) == 2: - yield path[1].rstrip() + yield path[1] return gen_list(result) diff --git a/pywb/utils.py b/pywb/utils.py index f2db7365..ea5f5179 100644 --- a/pywb/utils.py +++ b/pywb/utils.py @@ -4,6 +4,7 @@ import time import zlib import time import datetime +import calendar import re def peek_iter(iterable): @@ -25,6 +26,9 @@ def split_prefix(key, prefixs): def create_decompressor(): return zlib.decompressobj(16 + zlib.MAX_WBITS) +#================================================================= +# Cookie Signing +#================================================================= class HMACCookieMaker: def __init__(self, key, name): @@ -53,6 +57,7 @@ class HMACCookieMaker: #return cookie + hexdigest +#================================================================= # Adapted from example at class PerfTimer: def __init__(self, perfdict, name): @@ -69,8 +74,18 @@ class PerfTimer: self.perfdict[self.name] = str(self.end - self.start) +#================================================================= +# str <-> datetime conversion +#================================================================= + DATE_TIMESPLIT = re.compile('[^\d]') +TIMESTAMP_14 = '%Y%m%d%H%M%S' + +PAD_STAMP_END = '29991231235959' + + + def iso_date_to_datetime(string): """ >>> iso_date_to_datetime('2013-12-26T10:11:12Z') @@ -93,7 +108,7 @@ def datetime_to_timestamp(dt): '20131226101112' """ - return dt.strftime('%Y%m%d%H%M%S') + return dt.strftime(TIMESTAMP_14) def iso_date_to_timestamp(string): """ @@ -107,6 +122,52 @@ def iso_date_to_timestamp(string): return datetime_to_timestamp(iso_date_to_datetime(string)) +# default pad is end of range for compatibility +def pad_timestamp(string, pad_str = PAD_STAMP_END): + """ + >>> pad_timestamp('20') + '20991231235959' + + >>> pad_timestamp('2014') + '20141231235959' + + >>> pad_timestamp('20141011') + '20141011235959' + + >>> pad_timestamp('201410110010') + '20141011001059' + """ + + str_len = len(string) + pad_len = len(pad_str) + + return string if str_len >= pad_len else string + pad_str[str_len:] + + +def timestamp_to_datetime(string): + """ + >>> timestamp_to_datetime('20131226095010') + time.struct_time(tm_year=2013, tm_mon=12, tm_mday=26, tm_hour=9, tm_min=50, tm_sec=10, tm_wday=3, tm_yday=360, tm_isdst=-1) + + >>> timestamp_to_datetime('2014') + time.struct_time(tm_year=2014, tm_mon=12, tm_mday=31, tm_hour=23, tm_min=59, tm_sec=59, tm_wday=2, tm_yday=365, tm_isdst=-1) + """ + + # Default pad to end of range for comptability + return time.strptime(pad_timestamp(string), TIMESTAMP_14) + + +def timestamp_to_sec(string): + """ + >>> timestamp_to_sec('20131226095010') + 1388051410 + + >>> timestamp_to_sec('2014') + 1420070399 + """ + + return calendar.timegm(timestamp_to_datetime(string)) + # adapted -from wsgiref.request_uri, but doesn't include domain name and allows all characters # allowed in the path segment according to: http://tools.ietf.org/html/rfc3986#section-3.3 # explained here: http://stackoverflow.com/questions/4669692/valid-characters-for-directory-part-of-a-url-for-short-links diff --git a/test/dupes.cdx b/test/dupes.cdx new file mode 100644 index 00000000..4535c5e5 --- /dev/null +++ b/test/dupes.cdx @@ -0,0 +1,13 @@ + CDX N b a m s k r M S V g +com,example)/ 20140127171200 http://example.com text/html 200 B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 1046 334 dupes.warc.gz +com,example)/ 20140127171251 http://example.com warc/revisit - B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 553 11875 dupes.warc.gz +org,iana)/ 20140127171238 http://iana.org unk 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 343 1858 dupes.warc.gz +org,iana)/ 20140127171238 http://www.iana.org/ warc/revisit - OSSAPWJ23L56IYVRW3GFEAR4MCJMGPTB - - 536 2678 dupes.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140127171240 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 556 10826 dupes.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140127171240 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 540 9793 dupes.warc.gz +org,iana)/_css/2013.1/print.css 20140127171239 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 537 6684 dupes.warc.gz +org,iana)/_css/2013.1/screen.css 20140127171239 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 541 4630 dupes.warc.gz +org,iana)/_img/2013.1/iana-logo-homepage.png 20140127171240 http://www.iana.org/_img/2013.1/iana-logo-homepage.png warc/revisit - GCW2GM3SIMHEIQYZX25MLSRYVWUCZ7OK - - 549 8750 dupes.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140127171239 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 549 7709 dupes.warc.gz +org,iana)/_js/2013.1/iana.js 20140127171239 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 457 3696 dupes.warc.gz +org,iana)/_js/2013.1/jquery.js 20140127171239 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 547 5658 dupes.warc.gz diff --git a/test/dupes.warc.gz b/test/dupes.warc.gz new file mode 100644 index 00000000..48e6b6fd Binary files /dev/null and b/test/dupes.warc.gz differ diff --git a/test/example.cdx b/test/example.cdx new file mode 100644 index 00000000..56d75137 --- /dev/null +++ b/test/example.cdx @@ -0,0 +1,3 @@ + CDX N b a m s k r M S V g +com,example)/?example=1 20140103030321 http://example.com?example=1 text/html 200 B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 1043 333 example.warc.gz +com,example)/?example=1 20140103030341 http://example.com?example=1 warc/revisit - B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 553 1864 example.warc.gz diff --git a/test/iana.cdx b/test/iana.cdx new file mode 100644 index 00000000..a1e15806 --- /dev/null +++ b/test/iana.cdx @@ -0,0 +1,172 @@ + CDX N b a m s k r M S V g +org,iana)/ 20140126200624 http://www.iana.org/ text/html 200 OSSAPWJ23L56IYVRW3GFEAR4MCJMGPTB - - 2258 334 iana.warc.gz +org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126200826 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf application/octet-stream 200 LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 34054 620049 iana.warc.gz +org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126200912 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf warc/revisit - LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 546 667073 iana.warc.gz +org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126200930 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf warc/revisit - LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 534 697255 iana.warc.gz +org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126201055 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf warc/revisit - LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 547 714833 iana.warc.gz +org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126201249 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf warc/revisit - LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 551 768625 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200625 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf application/octet-stream 200 YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 117166 198285 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200654 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 548 482544 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200706 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 552 495230 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200718 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 536 566542 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200738 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 552 578743 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200805 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 535 593400 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200816 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 554 608401 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200826 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 550 654593 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200912 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 553 670224 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126200930 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 551 699343 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126201055 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 552 712719 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126201128 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 554 731718 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126201228 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 551 745730 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126201240 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 551 757988 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126201249 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 552 771773 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126201308 https://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 551 783712 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200626 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf application/octet-stream 200 GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 114499 83293 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200654 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 550 446529 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200706 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 553 493141 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200718 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 554 567576 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200738 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 555 580835 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200805 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 551 595503 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200816 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 554 609468 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200826 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 551 655640 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200912 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 551 669172 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126200930 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 553 698287 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126201055 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 553 711664 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126201128 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 553 730663 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126201228 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 537 743642 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126201240 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 552 755896 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126201249 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 553 769676 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126201308 https://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 551 784758 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126200654 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf application/octet-stream 200 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 116641 329393 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126200706 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 538 494192 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126200718 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 538 565504 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126200738 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 539 579795 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126200805 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 555 592333 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126200816 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 556 607332 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126200826 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 556 656690 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126200912 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 554 668113 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126200930 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 556 700397 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126201055 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 555 713774 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126201128 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 556 732779 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126201228 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 538 744686 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126201240 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 537 756949 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126201249 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 539 770730 iana.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126201308 https://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 554 782657 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200625 http://www.iana.org/_css/2013.1/print.css text/css 200 VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 4662 50482 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200653 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 534 326315 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200706 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 534 487982 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200716 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 535 561375 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200737 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 536 574583 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200804 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 538 588168 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200816 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 537 602081 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200825 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 535 613943 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200912 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 536 662904 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126200929 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 537 693076 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126201054 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 526 707519 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126201127 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 525 726489 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126201227 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 527 738432 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126201239 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 526 750710 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126201248 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 535 763424 iana.warc.gz +org,iana)/_css/2013.1/print.css 20140126201307 https://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 539 777477 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200625 http://www.iana.org/_css/2013.1/screen.css text/css 200 BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 8754 41238 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200653 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 533 328367 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200706 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 539 489005 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200716 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 542 563417 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200737 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 528 572623 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200804 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 527 589212 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200816 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 528 603125 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200825 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 527 614971 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200912 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 531 661876 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126200929 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 538 691096 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126201054 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 543 706476 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126201127 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 543 725445 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126201227 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 543 739461 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126201239 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 541 751731 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126201248 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 541 764454 iana.warc.gz +org,iana)/_css/2013.1/screen.css 20140126201307 https://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 537 779533 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126200654 http://www.iana.org/_img/2013.1/iana-logo-header.svg image/svg+xml 200 N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 9739 447577 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126200706 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 553 491049 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126200718 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 551 564454 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126200737 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 550 576643 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126200805 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 552 591269 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126200816 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 552 605204 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126200826 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 552 617954 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126200912 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 553 664967 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126200929 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 550 695150 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126201054 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 548 709577 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126201128 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 552 728551 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126201228 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 548 741538 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126201239 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 549 753801 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126201249 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 551 766525 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126201307 https://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 552 780562 iana.warc.gz +org,iana)/_img/2013.1/iana-logo-homepage.png 20140126200625 http://www.iana.org/_img/2013.1/iana-logo-homepage.png image/png 200 GCW2GM3SIMHEIQYZX25MLSRYVWUCZ7OK - - 27163 55631 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200625 http://www.iana.org/_img/2013.1/icann-logo.svg image/svg+xml 200 HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 2809 4009 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200654 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 546 457816 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200706 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 545 492101 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200719 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 548 568628 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200738 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 548 577695 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200805 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 547 594444 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200816 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 548 606272 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200826 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 545 619007 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200912 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 547 666025 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126200930 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 547 696207 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126201055 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 529 710633 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126201128 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 549 729609 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126201228 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 544 742593 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126201240 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 546 754853 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126201249 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 544 767580 iana.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126201308 https://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 546 781613 iana.warc.gz +org,iana)/_img/2013.1/rir-map.svg 20140126200654 http://www.iana.org/_img/2013.1/rir-map.svg image/svg+xml 200 C4LTM7ATRZYZL3W2UCEEX6A26L6PIT4K - - 23189 458860 iana.warc.gz +org,iana)/_img/bookmark_icon.ico 20140126200631 http://www.iana.org/_img/bookmark_icon.ico application/octet-stream 200 PG3PAWWE72JQ37CXJSPCJNNF7QI3SNX7 - - 4968 315944 iana.warc.gz +org,iana)/_img/bookmark_icon.ico 20140126201310 https://www.iana.org/_img/bookmark_icon.ico warc/revisit - PG3PAWWE72JQ37CXJSPCJNNF7QI3SNX7 - - 548 785806 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200625 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 458 3074 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200653 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 456 325380 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200706 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 458 487044 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200716 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 457 560436 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200737 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 457 573645 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200804 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 460 587215 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200816 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 459 601126 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200825 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 458 615991 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200912 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 456 660937 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126200929 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 458 692132 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126201054 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 456 705534 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126201127 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 457 724500 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126201227 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 458 737484 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126201239 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 457 749770 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126201248 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 458 762480 iana.warc.gz +org,iana)/_js/2013.1/iana.js 20140126201307 https://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 453 776543 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200625 http://www.iana.org/_js/2013.1/jquery.js application/x-javascript 200 AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 33449 7311 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200653 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 542 327341 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200706 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 529 490037 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200716 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 529 562402 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200737 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 543 575613 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200804 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 530 590244 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200816 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 544 604162 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200825 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 543 616929 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200912 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 544 663936 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126200929 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 546 694112 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126201054 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 544 708544 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126201127 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 545 727515 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126201227 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 543 740505 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126201239 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 545 752769 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126201248 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 544 765491 iana.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126201307 https://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 543 778507 iana.warc.gz +org,iana)/about 20140126200706 http://www.iana.org/about text/html 200 6G77LZKFAVKH4PCWWKMW6TRJPSHWUBI3 - - 2962 483588 iana.warc.gz +org,iana)/about/performance/ietf-draft-status 20140126200815 http://www.iana.org/about/performance/ietf-draft-status text/html 302 Y7CTA2QZUSCDTJCSECZNSPIBLJDO7PJJ - - 584 596566 iana.warc.gz +org,iana)/about/performance/ietf-statistics 20140126200804 http://www.iana.org/about/performance/ietf-statistics text/html 302 HNYDN7XRX46RQTT2OFIWXKEYMZQAJWHD - - 582 581890 iana.warc.gz +org,iana)/dnssec 20140126201306 http://www.iana.org/dnssec text/html 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 442 772827 iana.warc.gz +org,iana)/dnssec 20140126201307 https://www.iana.org/dnssec text/html 200 PHLRSX73EV3WSZRFXMWDO6BRKTVUSASI - - 2278 773766 iana.warc.gz +org,iana)/domains 20140126200825 http://www.iana.org/domains text/html 200 7UPSCLNWNZP33LGW6OJGSF2Y4CDG4ES7 - - 2912 610534 iana.warc.gz +org,iana)/domains/arpa 20140126201248 http://www.iana.org/domains/arpa text/html 200 QOFZZRN6JIKAL2JRL6ZC2VVG42SPKGHT - - 2939 759039 iana.warc.gz +org,iana)/domains/idn-tables 20140126201127 http://www.iana.org/domains/idn-tables text/html 200 HNCUFTJMOQOGAEY6T56KVC3T7TVLKGEW - - 8118 715878 iana.warc.gz +org,iana)/domains/int 20140126201239 http://www.iana.org/domains/int text/html 200 X32BBNNORV4SPEHTQF5KI5NFHSKTZK6Q - - 2482 746788 iana.warc.gz +org,iana)/domains/reserved 20140126201054 http://www.iana.org/domains/reserved text/html 200 R5AAEQX5XY5X5DG66B23ODN5DUBWRA27 - - 3573 701457 iana.warc.gz +org,iana)/domains/root 20140126200912 http://www.iana.org/domains/root text/html 200 YWA2R6UVWCYNHBZJKBTPYPZ5CJWKGGUX - - 2691 657746 iana.warc.gz +org,iana)/domains/root/db 20140126200927 http://www.iana.org/domains/root/db/ text/html 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 446 671278 iana.warc.gz +org,iana)/domains/root/db 20140126200928 http://www.iana.org/domains/root/db text/html 200 DHXA725IW5VJJFRTWBQT6BEZKRE7H57S - - 18365 672225 iana.warc.gz +org,iana)/domains/root/servers 20140126201227 http://www.iana.org/domains/root/servers text/html 200 AFW34N3S4NK2RJ6QWMVPB5E2AIUETAHU - - 3137 733840 iana.warc.gz +org,iana)/numbers 20140126200651 http://www.iana.org/numbers text/html 200 HWT5UZKURYLW5QNWVZCWFCANGEMU7XWK - - 3498 321385 iana.warc.gz +org,iana)/performance/ietf-draft-status 20140126200815 http://www.iana.org/performance/ietf-draft-status text/html 200 T5IQTX6DWV5KABGH454CYEDWKRI5Y23E - - 2940 597667 iana.warc.gz +org,iana)/performance/ietf-statistics 20140126200804 http://www.iana.org/performance/ietf-statistics text/html 200 XOFML5WNBQMTSULLIIPLSP6U5MX33HN6 - - 3712 582987 iana.warc.gz +org,iana)/protocols 20140126200715 http://www.iana.org/protocols text/html 200 IRUJZEUAXOUUG224ZMI4VWTUPJX6XJTT - - 63663 496277 iana.warc.gz +org,iana)/time-zones 20140126200737 http://www.iana.org/time-zones text/html 200 4Z27MYWOSXY2XDRAJRW7WRMT56LXDD4R - - 2449 569675 iana.warc.gz diff --git a/test/iana.warc.gz b/test/iana.warc.gz new file mode 100644 index 00000000..3a88a71a Binary files /dev/null and b/test/iana.warc.gz differ diff --git a/test/test.cdx b/test/test.cdx new file mode 100644 index 00000000..008eb374 --- /dev/null +++ b/test/test.cdx @@ -0,0 +1,193 @@ + CDX N b a m s k r M S V g +gov,nist)/ 20140126192426 http://www.nist.gov/ warc/revisit - PQFFO2MQ3SX7TFYUQL3ZFQCUI2PVJ7GJ - - 667 336 test.warc.gz +gov,nist)/commonspot/javascript/browser-all.js 20140126192427 http://www.nist.gov/commonspot/javascript/browser-all.js application/x-javascript 200 SPCVZQLHVLCC3X7A6P23TK6VYQ525UZX - - 3972 1486 test.warc.gz +gov,nist)/commonspot/commonspot.css 20140126192427 http://www.nist.gov/commonspot/commonspot.css text/css 200 RTD2ZTDVHEGUXEPUFJUKK42T6E6TZGQM - - 4374 5998 test.warc.gz +gov,nist)/style/nist-styles.css 20140126192427 http://www.nist.gov/style/nist-styles.css warc/revisit - YHQ23OGXPSN7QVAHA3JB5D2SR45XG67P - - 547 10909 test.warc.gz +gov,nist)/style/nist-subsite-overrides.css 20140126192427 http://www.nist.gov/style/nist-subsite-overrides.css warc/revisit - 76STS6E3XWIMQE4UKLK45R2HCAZHOJGS - - 557 11992 test.warc.gz +gov,nist)/style/default.css 20140126192427 http://www.nist.gov/style/default.css warc/revisit - 2LF345KIR7K2D72RTGD5YZP7XC767TFB - - 550 13096 test.warc.gz +gov,nist)/js/federated-analytics.all.min.js?agency=nist&pua=ua-37115410-1&yt=true 20140126192427 http://www.nist.gov/js/federated-analytics.all.min.js?agency=NIST&pua=UA-37115410-1&yt=true warc/revisit - TUQLSDJSE6AJMHX7WMRPYDBKHJODDSNI - - 605 14181 test.warc.gz +gov,nist)/js/nist-exit-script.js 20140126192427 http://www.nist.gov/js/nist-exit-script.js warc/revisit - ZNR7SPZGPS5QN4EZPPPZDAY7FK3LBNLU - - 557 15357 test.warc.gz +com,googleapis,ajax)/ajax/libs/jquery/1.7.2/jquery.min.js 20140126192427 http://ajax.googleapis.com/ajax/libs/jquery/1.7.2/jquery.min.js warc/revisit - VPGSXIJTJDYXRMLRIG2ELPEZ6GIX2R5P - - 654 16444 test.warc.gz +gov,nist)/customcf/foresee/foresee-trigger.js 20140126192428 http://www.nist.gov/customcf/foresee/foresee-trigger.js application/x-javascript 200 KSIRZ6JKRLFCT2WAJQCY2JFHTR7URPSI - - 19202 17601 test.warc.gz +gov,nist)/commonspot/pagemode/always-include-common.js 20140126192428 http://www.nist.gov/commonspot/pagemode/always-include-common.js application/x-javascript 200 5KGH5UFBOJYFYIIUXPOR5M6AU7JTESPJ - - 1045 37340 test.warc.gz +gov,nist)/commonspot/pagemode/always-include-ns.js 20140126192428 http://www.nist.gov/commonspot/pagemode/always-include-ns.js application/x-javascript 200 F3YIXDMUEIYFQAMBQDRQHIR67ODARWKS - - 1605 38932 test.warc.gz +com,google,translate)/translate_a/element.js?cb=googletranslateelementinit 20140126192428 http://translate.google.com/translate_a/element.js?cb=googleTranslateElementInit text/javascript 200 HVWT4O5N3AGO2OYUJ3B6JVIYDWTSN3R5 - - 1269 41083 test.warc.gz +gov,nist)/images/banner_graphics/homepage_banner.jpg 20140126192428 http://www.nist.gov/images/banner_graphics/homepage_banner.jpg warc/revisit - ICDGUE3GD4SDQTUWOI4ROQSJAZYTL6GZ - - 561 42860 test.warc.gz +gov,nist)/style/sliderstyles/default.css 20140126192428 http://www.nist.gov/style/sliderstyles/default.css warc/revisit - MQRO2VAVYQF7V52LWHQNVYYCMEG3PTPA - - 560 43973 test.warc.gz +gov,nist)/js/slides/slides.min.jquery.js 20140126192428 http://www.nist.gov/js/slides/slides.min.jquery.js warc/revisit - 763DGAWKGMQVAFFIPU2BDBPBNGXCY474 - - 570 45077 test.warc.gz +gov,nist)/style/web_fonts/functionpro_medium_macroman/functionpro-medium-webfont.woff 20140126192428 http://www.nist.gov/style/web_fonts/functionpro_medium_macroman/FunctionPro-Medium-webfont.woff warc/revisit - LA2T54OTXUBZDA7WMZHH3R46Z3MXL3VB - - 608 46183 test.warc.gz +gov,nist)/images/banner_graphics/curvy_topline.jpg 20140126192428 http://www.nist.gov/images/banner_graphics/curvy_topline.jpg warc/revisit - T6U7764QBDOIEE2SIZC32TQ74WHJNC7O - - 560 47355 test.warc.gz +gov,nist)/images/13pml041_strontium_clock_cropped_cs.jpg 20140126192428 http://www.nist.gov/images/13PML041_strontium_clock_cropped_CS.jpg image/jpeg 200 QQW5JIAJKNA2QNSN5NPUEPVXHDSTICTC - - 85057 48466 test.warc.gz +gov,nist)/images/ui/blue_greybanner.gif 20140126192428 http://www.nist.gov/images/ui/blue_greyBanner.gif warc/revisit - 7D4IHRCXVE4MWGXSF7VPDABJ4JJJ2V2K - - 550 134081 test.warc.gz +com,google-analytics)/ga.js 20140126192428 http://www.google-analytics.com/ga.js warc/revisit - ECJWCGSLO7C3X7JYGORGFIGOWQKCKXPX - - 579 135173 test.warc.gz +gov,nist)/images/ui/separation_dots.gif 20140126192429 http://www.nist.gov/images/ui/separation_dots.gif warc/revisit - CLCSX5BETYEWLSSV7BPJ3WWLOQRNQJVS - - 548 136236 test.warc.gz +gov,nist)/style/images/frontpagesprite.png 20140126192429 http://www.nist.gov/style/images/frontpagesprite.png warc/revisit - XUXHDOJKIYLVUHBKNSCLKOPBP7UYDNVL - - 545 137326 test.warc.gz +gov,nist)/images/14itl001_oneshot_memory_cs.jpg 20140126192429 http://www.nist.gov/images/14ITL001_oneshot_memory_CS.jpg warc/revisit - R5T7WIDVFYLUIA7VIG4MU6547KJAXANS - - 556 138414 test.warc.gz +gov,nist)/images/13pml041_strontium_clock_cropped_cs.jpg?1390764269346 20140126192429 http://www.nist.gov/images/13PML041_strontium_clock_cropped_CS.jpg?1390764269346 image/jpeg 200 QQW5JIAJKNA2QNSN5NPUEPVXHDSTICTC - - 85072 139522 test.warc.gz +gov,nist)/js/slides/img/loading.gif 20140126192429 http://www.nist.gov/js/slides/img/loading.gif warc/revisit - RGFSZQVIWGUZ6YTFK5FJSRNJCTURHK4P - - 550 225163 test.warc.gz +gov,nist)/public_affairs/images/14el001_mwnt_coating_composite_cs.jpg 20140126192429 http://www.nist.gov/public_affairs/images/14EL001_mwnt_coating_composite_CS.jpg warc/revisit - SYXA53HAYYQRM4KO6T545DDYNHMITK4X - - 572 226255 test.warc.gz +gov,nist)/images/14do001_doe_video_screen_cs.jpg 20140126192429 http://www.nist.gov/images/14DO001_doe_video_screen_CS.jpg warc/revisit - TPVX2DT74WBMBPNHCXYMXXED3B73XMAE - - 556 227393 test.warc.gz +com,google-analytics)/__utm.gif?aip=1&utmac=ua-33523145-1&utmcc=__utma=165374137.1242695617.1390763971.1390763971.1390763971.1;+__utmz=165374137.1390763971.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none);&utmcs=utf-8&utmdt=national%20institute%20of%20standards%20and%20technology&utme=8(33!agency*sub-agency*code%20ver)9(33!nist*nist%20-%20wwwb-app5.us.archive.org*v1.7%20130503%20:%20single%20file%20version)&utmfl=11.9%20r900&utmhid=1034657774&utmhn=wwwb-app5.us.archive.org&utmht=1390764270100&utmje=1&utmmt=1&utmn=653677880&utmp=/save/http://www.nist.gov/&utmr=-&utms=5&utmsc=24-bit&utmsr=1366x768&utmu=qrsgaaaamaaaaaaaaaaaaq~&utmul=en-us&utmvp=1351x632&utmwv=5.4.6 20140126192429 http://www.google-analytics.com/__utm.gif?utmwv=5.4.6&utms=5&utmn=653677880&utmhn=wwwb-app5.us.archive.org&utme=8(33!Agency*Sub-Agency*Code%20Ver)9(33!NIST*NIST%20-%20wwwb-app5.us.archive.org*v1.7%20130503%20%3A%20Single%20File%20Version)&utmcs=UTF-8&utmsr=1366x768&utmvp=1351x632&utmsc=24-bit&utmul=en-us&utmje=1&utmfl=11.9%20r900&utmdt=National%20Institute%20of%20Standards%20and%20Technology&utmhid=1034657774&utmr=-&utmp=%2Fsave%2Fhttp%3A%2F%2Fwww.nist.gov%2F&utmht=1390764270100&utmac=UA-33523145-1&utmcc=__utma%3D165374137.1242695617.1390763971.1390763971.1390763971.1%3B%2B__utmz%3D165374137.1390763971.1.1.utmcsr%3D(direct)%7Cutmccn%3D(direct)%7Cutmcmd%3D(none)%3B&aip=1&utmmt=1&utmu=qRSgAAAAMAAAAAAAAAAAAQ~ image/gif 200 B5HJFHOVXMSWJ55LTR3DHDQE4KJKIKWO - - 946 228502 test.warc.gz +com,google-analytics)/__utm.gif?aip=1&utmac=ua-37115410-1&utmcc=__utma=165374137.1242695617.1390763971.1390763971.1390763971.1;+__utmz=165374137.1390763971.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none);&utmcs=utf-8&utmdt=national%20institute%20of%20standards%20and%20technology&utme=8(33!agency*sub-agency*code%20ver)9(33!nist*nist%20-%20wwwb-app5.us.archive.org*v1.7%20130503%20:%20single%20file%20version)&utmfl=11.9%20r900&utmhid=1034657774&utmhn=wwwb-app5.us.archive.org&utmht=1390764270115&utmje=1&utmmt=1&utmn=1702658108&utmp=/save/http://www.nist.gov/&utmr=-&utms=6&utmsc=24-bit&utmsr=1366x768&utmu=qrsgaaaamaaaaaaaaaaaaq~&utmul=en-us&utmvp=1351x632&utmwv=5.4.6 20140126192429 http://www.google-analytics.com/__utm.gif?utmwv=5.4.6&utms=6&utmn=1702658108&utmhn=wwwb-app5.us.archive.org&utme=8(33!Agency*Sub-Agency*Code%20Ver)9(33!NIST*NIST%20-%20wwwb-app5.us.archive.org*v1.7%20130503%20%3A%20Single%20File%20Version)&utmcs=UTF-8&utmsr=1366x768&utmvp=1351x632&utmsc=24-bit&utmul=en-us&utmje=1&utmfl=11.9%20r900&utmdt=National%20Institute%20of%20Standards%20and%20Technology&utmhid=1034657774&utmr=-&utmp=%2Fsave%2Fhttp%3A%2F%2Fwww.nist.gov%2F&utmht=1390764270115&utmac=UA-37115410-1&utmcc=__utma%3D165374137.1242695617.1390763971.1390763971.1390763971.1%3B%2B__utmz%3D165374137.1390763971.1.1.utmcsr%3D(direct)%7Cutmccn%3D(direct)%7Cutmcmd%3D(none)%3B&aip=1&utmmt=1&utmu=qRSgAAAAMAAAAAAAAAAAAQ~ image/gif 200 B5HJFHOVXMSWJ55LTR3DHDQE4KJKIKWO - - 946 230329 test.warc.gz +gov,nist)/images/13pml041_strontium_clock_cropped_cs.jpg?1390764278987 20140126192439 http://www.nist.gov/images/13PML041_strontium_clock_cropped_CS.jpg?1390764278987 image/jpeg 200 QQW5JIAJKNA2QNSN5NPUEPVXHDSTICTC - - 85070 232156 test.warc.gz +org,w3c)/ 20140126192448 http://w3c.org unk 301 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 342 317796 test.warc.gz +org,w3)/ 20140126192450 http://www.w3.org/ text/html 200 VC4E36NYEBSJUZEKL6C475PF47BF2UPT - - 10023 318615 test.warc.gz +org,w3)/2008/site/css/minimum 20140126192451 http://www.w3.org/2008/site/css/minimum warc/revisit - YDV254TDSTDXNHINXRXKYKWC5S25CD33 - - 644 329119 test.warc.gz +org,w3)/2008/site/images/search-button 20140126192451 http://www.w3.org/2008/site/images/search-button warc/revisit - QOG5YXVGKAUFETSAZ65ZWKQN7O3KAVJA - - 638 330251 test.warc.gz +org,w3)/2008/site/images/logo-shadow 20140126192451 http://www.w3.org/2008/site/images/logo-shadow warc/revisit - JE7KD4BEARSKUOHPQTP4RKMMWUUKFRFY - - 636 331381 test.warc.gz +org,w3)/2008/site/images/logo-w3c-mobile-lg 20140126192451 http://www.w3.org/2008/site/images/logo-w3c-mobile-lg warc/revisit - BMRUVXB5J3JWOLCOOFYEDUK6UILIASBY - - 644 332508 test.warc.gz +org,w3)/2008/site/images/header-link.gif 20140126192451 http://www.w3.org/2008/site/images/header-link.gif warc/revisit - X75XFMDM46YSREHW6VE4QRON7XSYKJVZ - - 595 333649 test.warc.gz +org,w3)/2008/site/css/print 20140126192452 http://www.w3.org/2008/site/css/print warc/revisit - BKUBBT5NEAIJ5CSYQFWH2JCPD3UXMR6B - - 642 334738 test.warc.gz +org,w3)/2008/site/images/icons/rss30 20140126192452 http://www.w3.org/2008/site/images/icons/rss30 warc/revisit - 6OMO6CFICZN5AZAIJ3AV3APIZG77XYD2 - - 638 335864 test.warc.gz +org,w3)/2008/site/css/advanced 20140126192452 http://www.w3.org/2008/site/css/advanced warc/revisit - QDWHZOP247JGRNWHHFXKE5HOJA4EVJUF - - 653 336993 test.warc.gz +org,w3)/2008/site/images/icons/atom30 20140126192453 http://www.w3.org/2008/site/images/icons/atom30 warc/revisit - KRJ3TY6U4CK5TCNZGZY5AQR2Y6S53O4A - - 635 338135 test.warc.gz +org,w3)/2008/site/css/realprint.css 20140126192453 http://www.w3.org/2008/site/css/realprint.css warc/revisit - VZ2UOR2I6WGU4ZMA3C6DAIDRFBIB3CBC - - 594 339262 test.warc.gz +org,w3)/2008/site/images/header-link 20140126192453 http://www.w3.org/2008/site/images/header-link warc/revisit - X75XFMDM46YSREHW6VE4QRON7XSYKJVZ - - 634 340349 test.warc.gz +org,w3,validator-suite)/icons/vs-blue-256.svg 20140126192453 http://validator-suite.w3.org/icons/vs-blue-256.svg warc/revisit - IJIIFBZYTPZR75PPZUSSITV66XGV4SVE - - 477 341475 test.warc.gz +org,w3)/2008/site/images/category-bg-fold.png 20140126192453 http://www.w3.org/2008/site/images/category-bg-fold.png warc/revisit - ZK6MO433VCNDIRQYUGWZ2SDDIQFZSCFP - - 593 342452 test.warc.gz +org,w3)/2008/site/images/page/page_bkg.jpg 20140126192453 http://www.w3.org/2008/site/images/page/page_bkg.jpg warc/revisit - 2JS33DQF2XDILFBB2JE3BDJDOA7QM4FF - - 599 343544 test.warc.gz +org,w3)/2008/site/images/search-bg.png 20140126192453 http://www.w3.org/2008/site/images/search-bg.png warc/revisit - GI5GKXTIPV23XNVBXNSPGGT5J5NBZECB - - 591 344640 test.warc.gz +org,w3)/2008/site/images/logo-w3c-screen-lg 20140126192453 http://www.w3.org/2008/site/images/logo-w3c-screen-lg warc/revisit - PI67JKISUQ5Z4GNQE63TTYDHM3Y6L4UA - - 646 345724 test.warc.gz +org,w3)/2008/site/images/google 20140126192453 http://www.w3.org/2008/site/images/google warc/revisit - J4XLVFATF4IHPSLUMU2LPXXEUDQYR3PY - - 632 346867 test.warc.gz +org,w3)/2008/site/images/skip.png 20140126192454 http://www.w3.org/2008/site/images/skip.png warc/revisit - KYGR5HVCUVP3G2XHITC43CXG4W7IDOW5 - - 585 347986 test.warc.gz +org,w3)/2008/site/images/theme-all.png 20140126192454 http://www.w3.org/2008/site/images/theme-all.png warc/revisit - 7YRO3ZVZ3MO7YVQEDJEZ3RXXSKGLTFFZ - - 593 349060 test.warc.gz +org,w3)/2008/site/images/category-bg.png 20140126192454 http://www.w3.org/2008/site/images/category-bg.png warc/revisit - G6TZMIU3MCYZVEDPMC2DL4M6WLFWHKYA - - 592 350147 test.warc.gz +org,w3)/2008/site/images/talks-bg-left.png 20140126192454 http://www.w3.org/2008/site/images/talks-bg-left.png warc/revisit - YUTG7VQMNMX37DIOBPZ5Y5EK66UED3HI - - 591 351234 test.warc.gz +org,w3)/2008/site/images/talks-bg.png 20140126192454 http://www.w3.org/2008/site/images/talks-bg.png warc/revisit - 3J27MFEO6JE3HTIPYTWIJZBZ5UJUO5EI - - 585 352321 test.warc.gz +org,w3)/2008/site/images/talks-bg-right.png 20140126192454 http://www.w3.org/2008/site/images/talks-bg-right.png warc/revisit - EVI3SG6LZL46O53T6HGNX6FSXUBD77SE - - 595 353399 test.warc.gz +org,w3)/2008/site/js/main 20140126192454 http://www.w3.org/2008/site/js/main warc/revisit - RTZFXO6WDV4LUZVEVYDUVN4MJ4FGA3FJ - - 637 354492 test.warc.gz +org,w3)/2008/site/images/calendar-sprite.png 20140126192454 http://www.w3.org/2008/site/images/calendar-sprite.png warc/revisit - VL2SME5GZFNANSUNZ5VUBHCRAMVLMIJL - - 592 355604 test.warc.gz +org,w3)/2008/site/images/category-bg-right.png 20140126192455 http://www.w3.org/2008/site/images/category-bg-right.png warc/revisit - NW2WTWHNMK6J4CEQTI5H4JCG32XUSL7B - - 591 356691 test.warc.gz +org,w3)/consortium/member/testimonial/logo/775 20140126192455 http://www.w3.org/Consortium/Member/Testimonial/Logo/775 warc/revisit - NSXJLI4UOG666SDK5LNCY6YJ3GLDYNVJ - - 649 357782 test.warc.gz +org,w3,validator-suite)/icons/vs-blue-256.svg 20140126192453 https://validator-suite.w3.org/icons/vs-blue-256.svg warc/revisit - XJMWQPXPUTIP5EKDTGLQW6MUY4B4VW44 - - 716 358932 test.warc.gz +org,w3)/2008/site/images/footer-shadow.png 20140126192456 http://www.w3.org/2008/site/images/footer-shadow.png warc/revisit - RC2EPFVZLPHI33BEKZYNE5XZIP5Q6QXL - - 598 360151 test.warc.gz +org,w3)/2008/site/images/twitter-bird 20140126192456 http://www.w3.org/2008/site/images/twitter-bird warc/revisit - 4NMC2Y4ZJVGNHHSVHK4IU2H4QGMODUUD - - 638 361246 test.warc.gz +org,w3)/2008/site/images/identica-logo 20140126192456 http://www.w3.org/2008/site/images/identica-logo warc/revisit - 6M6LYDKOPIORHLHRWBZAZPBK5ZVGFLOX - - 635 362377 test.warc.gz +org,w3)/2008/site/js/lang/strings.js 20140126192456 http://www.w3.org/2008/site/js/lang/strings.js warc/revisit - OCTSZQXMRHO5XBL5FYCNCALL3JKP45NJ - - 658 363503 test.warc.gz +org,w3)/2008/site/images/ico-minus 20140126192456 http://www.w3.org/2008/site/images/ico-minus warc/revisit - 3W5VMCQOL56ZJ6QP3QL2SMWBETHXCHFN - - 632 364669 test.warc.gz +org,w3)/2008/site/images/ico-plus 20140126192456 http://www.w3.org/2008/site/images/ico-plus warc/revisit - ZBGPPB5UR7BLPFOJGZSDM7PNBJLECURY - - 633 365792 test.warc.gz +org,w3)/2008/site/images/favicon.ico 20140126192457 http://www.w3.org/2008/site/images/favicon.ico warc/revisit - 2SASTUEUQUZKXH5LWWYUFANTHXZGOBVT - - 586 366913 test.warc.gz +org,w3)/standards/webdesign 20140126192532 http://www.w3.org/standards/webdesign/ warc/revisit - WQSP2DY74HMWNERWQSXZLP3N4NFZZXYB - - 586 367976 test.warc.gz +org,w3)/2008/site/css/minimum 20140126192533 http://www.w3.org/2008/site/css/minimum warc/revisit - YDV254TDSTDXNHINXRXKYKWC5S25CD33 - - 643 369061 test.warc.gz +org,w3)/2008/site/images/logo-shadow 20140126192533 http://www.w3.org/2008/site/images/logo-shadow warc/revisit - JE7KD4BEARSKUOHPQTP4RKMMWUUKFRFY - - 636 370205 test.warc.gz +org,w3)/2008/site/images/search-button 20140126192533 http://www.w3.org/2008/site/images/search-button warc/revisit - QOG5YXVGKAUFETSAZ65ZWKQN7O3KAVJA - - 636 371345 test.warc.gz +org,w3)/2008/site/images/logo-w3c-mobile-lg 20140126192533 http://www.w3.org/2008/site/images/logo-w3c-mobile-lg warc/revisit - BMRUVXB5J3JWOLCOOFYEDUK6UILIASBY - - 644 372487 test.warc.gz +org,w3)/2008/site/css/advanced 20140126192533 http://www.w3.org/2008/site/css/advanced warc/revisit - QDWHZOP247JGRNWHHFXKE5HOJA4EVJUF - - 652 373641 test.warc.gz +org,w3)/2008/site/images/header-link 20140126192533 http://www.w3.org/2008/site/images/header-link warc/revisit - X75XFMDM46YSREHW6VE4QRON7XSYKJVZ - - 635 374794 test.warc.gz +org,w3)/2008/site/images/theme-web-design 20140126192533 http://www.w3.org/2008/site/images/theme-web-design warc/revisit - OCOJ2SSUXIR2V63AGVZCMSPSVZH6B3EI - - 640 375933 test.warc.gz +org,w3)/2008/site/css/print 20140126192533 http://www.w3.org/2008/site/css/print warc/revisit - BKUBBT5NEAIJ5CSYQFWH2JCPD3UXMR6B - - 642 377080 test.warc.gz +org,w3)/2008/site/images/category-bg-fold.png 20140126192534 http://www.w3.org/2008/site/images/category-bg-fold.png warc/revisit - ZK6MO433VCNDIRQYUGWZ2SDDIQFZSCFP - - 594 378222 test.warc.gz +org,w3)/2008/site/images/page/page_bkg.jpg 20140126192534 http://www.w3.org/2008/site/images/page/page_bkg.jpg warc/revisit - 2JS33DQF2XDILFBB2JE3BDJDOA7QM4FF - - 598 379328 test.warc.gz +org,w3)/2008/site/images/google 20140126192534 http://www.w3.org/2008/site/images/google warc/revisit - J4XLVFATF4IHPSLUMU2LPXXEUDQYR3PY - - 633 380435 test.warc.gz +org,w3)/2008/site/images/search-bg.png 20140126192534 http://www.w3.org/2008/site/images/search-bg.png warc/revisit - GI5GKXTIPV23XNVBXNSPGGT5J5NBZECB - - 591 381567 test.warc.gz +org,w3)/2008/site/images/logo-w3c-screen-lg 20140126192534 http://www.w3.org/2008/site/images/logo-w3c-screen-lg warc/revisit - PI67JKISUQ5Z4GNQE63TTYDHM3Y6L4UA - - 647 382664 test.warc.gz +org,w3)/2008/site/js/main 20140126192534 http://www.w3.org/2008/site/js/main warc/revisit - RTZFXO6WDV4LUZVEVYDUVN4MJ4FGA3FJ - - 637 383820 test.warc.gz +org,w3)/2008/site/images/skip.png 20140126192534 http://www.w3.org/2008/site/images/skip.png warc/revisit - KYGR5HVCUVP3G2XHITC43CXG4W7IDOW5 - - 586 384947 test.warc.gz +org,w3)/2008/site/images/bct.png 20140126192534 http://www.w3.org/2008/site/images/bct.png warc/revisit - WOQ2FH33THZ2FNKFVPMAOKYJOZW7RXUD - - 583 386035 test.warc.gz +org,w3)/2008/site/images/category-bg.png 20140126192534 http://www.w3.org/2008/site/images/category-bg.png warc/revisit - G6TZMIU3MCYZVEDPMC2DL4M6WLFWHKYA - - 593 387118 test.warc.gz +org,w3)/2008/site/css/realprint.css 20140126192534 http://www.w3.org/2008/site/css/realprint.css warc/revisit - VZ2UOR2I6WGU4ZMA3C6DAIDRFBIB3CBC - - 596 388218 test.warc.gz +org,w3)/2008/site/images/icons/atom30 20140126192534 http://www.w3.org/2008/site/images/icons/atom30 warc/revisit - KRJ3TY6U4CK5TCNZGZY5AQR2Y6S53O4A - - 638 389319 test.warc.gz +com,wp,s0)/wp-includes/images/smilies/icon_smile.gif 20140126192535 http://s0.wp.com/wp-includes/images/smilies/icon_smile.gif image/gif 200 JXHAUHA5WC7VGIPFWMTQX66BWBM243XS - - 698 390462 test.warc.gz +com,wordpress,stats)/b.gif?blog=557157&feed=1&host=ivan-herman.name&post=1033&ref=&subd=ivanherman 20140126192535 http://stats.wordpress.com/b.gif?host=ivan-herman.name&blog=557157&post=1033&subd=ivanherman&ref=&feed=1 warc/revisit - XAFRCIB5S77ADRKZPSR344CAN2SI6VYJ - - 561 391678 test.warc.gz +com,flickr,static,farm6)/5482/10919013103_749a746640_m.jpg 20140126192535 http://farm6.static.flickr.com/5482/10919013103_749a746640_m.jpg warc/revisit - AZ7G626S3E6FIDTLEJTRE4HBIMWKQECV - - 798 392793 test.warc.gz +com,zemanta,img)/pixy.gif?x-id=87dd6914-e96a-4ef9-a83c-e1656d939cc8 20140126192535 http://img.zemanta.com/pixy.gif?x-id=87dd6914-e96a-4ef9-a83c-e1656d939cc8 image/gif 200 JYE7EYE2BD2K3F7JLSYAWWX3B3SRWQXU - - 1488 394118 test.warc.gz +com,zemanta,img)/pixy.gif?x-id=f92d4f05-2761-4b1f-bee8-64650d069005 20140126192535 http://img.zemanta.com/pixy.gif?x-id=f92d4f05-2761-4b1f-bee8-64650d069005 image/gif 200 JYE7EYE2BD2K3F7JLSYAWWX3B3SRWQXU - - 1489 396138 test.warc.gz +com,wordpress,feeds)/1.0/comments/ivanherman.wordpress.com/1033 20140126192535 http://feeds.wordpress.com/1.0/comments/ivanherman.wordpress.com/1033/ warc/revisit - 2ZMTV5SK7PRKIWVT3A2XCTCIDA23GTZQ - - 617 398162 test.warc.gz +com,wordpress,feeds)/1.0/comments/ivanherman.wordpress.com/1021 20140126192535 http://feeds.wordpress.com/1.0/comments/ivanherman.wordpress.com/1021/ warc/revisit - E35VUVLCAHOQ4FL2GXA6IBWJV5NDSCUL - - 618 399300 test.warc.gz +com,wordpress,stats)/b.gif?blog=557157&feed=1&host=ivan-herman.name&post=1021&ref=&subd=ivanherman 20140126192535 http://stats.wordpress.com/b.gif?host=ivan-herman.name&blog=557157&post=1021&subd=ivanherman&ref=&feed=1 warc/revisit - XAFRCIB5S77ADRKZPSR344CAN2SI6VYJ - - 561 400438 test.warc.gz +com,wordpress,files,ivanherman)/2013/08/a_dsc00143.jpg?h=219&w=390 20140126192535 http://ivanherman.files.wordpress.com/2013/08/a_dsc00143.jpg?w=390&h=219 warc/revisit - 3XSGBXR3CMIVRWB7C5WXQF5NY2WJR76X - - 577 401551 test.warc.gz +com,wordpress,stats)/b.gif?blog=557157&feed=1&host=ivan-herman.name&post=986&ref=&subd=ivanherman 20140126192535 http://stats.wordpress.com/b.gif?host=ivan-herman.name&blog=557157&post=986&subd=ivanherman&ref=&feed=1 warc/revisit - XAFRCIB5S77ADRKZPSR344CAN2SI6VYJ - - 562 402662 test.warc.gz +com,wordpress,feeds)/1.0/comments/ivanherman.wordpress.com/986 20140126192535 http://feeds.wordpress.com/1.0/comments/ivanherman.wordpress.com/986/ warc/revisit - JAC2MT7F45L6XV7GR33YJRKEDC5E33SW - - 620 403779 test.warc.gz +org,w3)/2008/site/images/twitter-bird 20140126192535 http://www.w3.org/2008/site/images/twitter-bird warc/revisit - 4NMC2Y4ZJVGNHHSVHK4IU2H4QGMODUUD - - 636 404918 test.warc.gz +org,w3)/2008/site/images/footer-shadow.png 20140126192536 http://www.w3.org/2008/site/images/footer-shadow.png warc/revisit - RC2EPFVZLPHI33BEKZYNE5XZIP5Q6QXL - - 598 406059 test.warc.gz +org,w3)/2008/site/images/talks-bg.png 20140126192536 http://www.w3.org/2008/site/images/talks-bg.png warc/revisit - 3J27MFEO6JE3HTIPYTWIJZBZ5UJUO5EI - - 585 407165 test.warc.gz +org,w3)/2008/site/images/talks-bg-left.png 20140126192536 http://www.w3.org/2008/site/images/talks-bg-left.png warc/revisit - YUTG7VQMNMX37DIOBPZ5Y5EK66UED3HI - - 593 408256 test.warc.gz +org,w3)/2008/site/images/talks-bg-right.png 20140126192536 http://www.w3.org/2008/site/images/talks-bg-right.png warc/revisit - EVI3SG6LZL46O53T6HGNX6FSXUBD77SE - - 594 409355 test.warc.gz +org,w3)/2008/site/images/calendar-sprite.png 20140126192536 http://www.w3.org/2008/site/images/calendar-sprite.png warc/revisit - VL2SME5GZFNANSUNZ5VUBHCRAMVLMIJL - - 593 410460 test.warc.gz +org,w3)/2008/site/images/ico-minus 20140126192536 http://www.w3.org/2008/site/images/ico-minus warc/revisit - 3W5VMCQOL56ZJ6QP3QL2SMWBETHXCHFN - - 634 411562 test.warc.gz +org,w3)/2008/site/images/ico-plus 20140126192537 http://www.w3.org/2008/site/images/ico-plus warc/revisit - ZBGPPB5UR7BLPFOJGZSDM7PNBJLECURY - - 631 412699 test.warc.gz +org,w3)/standards/webarch 20140126192556 http://www.w3.org/standards/webarch/ warc/revisit - 6DGR7P5H736TT7TCAG6WP6P3EGLJPRI4 - - 578 413832 test.warc.gz +org,w3)/2008/site/images/search-button 20140126192557 http://www.w3.org/2008/site/images/search-button warc/revisit - QOG5YXVGKAUFETSAZ65ZWKQN7O3KAVJA - - 637 414906 test.warc.gz +org,w3)/2008/site/css/print 20140126192557 http://www.w3.org/2008/site/css/print warc/revisit - BKUBBT5NEAIJ5CSYQFWH2JCPD3UXMR6B - - 641 416047 test.warc.gz +org,w3)/2008/site/images/logo-w3c-mobile-lg 20140126192557 http://www.w3.org/2008/site/images/logo-w3c-mobile-lg warc/revisit - BMRUVXB5J3JWOLCOOFYEDUK6UILIASBY - - 643 417187 test.warc.gz +org,w3)/2008/site/css/minimum 20140126192557 http://www.w3.org/2008/site/css/minimum warc/revisit - YDV254TDSTDXNHINXRXKYKWC5S25CD33 - - 643 418340 test.warc.gz +org,w3)/2008/site/css/advanced 20140126192557 http://www.w3.org/2008/site/css/advanced warc/revisit - QDWHZOP247JGRNWHHFXKE5HOJA4EVJUF - - 653 419483 test.warc.gz +org,w3)/2008/site/images/logo-shadow 20140126192557 http://www.w3.org/2008/site/images/logo-shadow warc/revisit - JE7KD4BEARSKUOHPQTP4RKMMWUUKFRFY - - 637 420636 test.warc.gz +org,w3)/2008/site/images/header-link 20140126192557 http://www.w3.org/2008/site/images/header-link warc/revisit - X75XFMDM46YSREHW6VE4QRON7XSYKJVZ - - 635 421778 test.warc.gz +org,w3)/2008/site/images/theme-web-arch 20140126192557 http://www.w3.org/2008/site/images/theme-web-arch warc/revisit - ZOOARJHNWK2OI7IM23LE6BHUBKOGCZVD - - 639 422915 test.warc.gz +org,w3)/2008/site/images/icons/atom30 20140126192558 http://www.w3.org/2008/site/images/icons/atom30 warc/revisit - KRJ3TY6U4CK5TCNZGZY5AQR2Y6S53O4A - - 634 424056 test.warc.gz +org,w3)/2008/site/js/main 20140126192557 http://www.w3.org/2008/site/js/main warc/revisit - RTZFXO6WDV4LUZVEVYDUVN4MJ4FGA3FJ - - 639 425193 test.warc.gz +org,w3)/2008/site/css/realprint.css 20140126192558 http://www.w3.org/2008/site/css/realprint.css warc/revisit - VZ2UOR2I6WGU4ZMA3C6DAIDRFBIB3CBC - - 594 426321 test.warc.gz +org,w3)/international/multilingualweb/images/mlw-logo.png 20140126192558 http://www.w3.org/International/multilingualweb/images/mlw-logo.png warc/revisit - R6SIVM5KSXTASGYMUXB36JXPBHDSUGFC - - 610 427418 test.warc.gz +org,w3)/2008/site/images/page/page_bkg.jpg 20140126192558 http://www.w3.org/2008/site/images/page/page_bkg.jpg warc/revisit - 2JS33DQF2XDILFBB2JE3BDJDOA7QM4FF - - 597 428546 test.warc.gz +org,w3)/2008/site/images/search-bg.png 20140126192558 http://www.w3.org/2008/site/images/search-bg.png warc/revisit - GI5GKXTIPV23XNVBXNSPGGT5J5NBZECB - - 590 429651 test.warc.gz +org,w3)/2008/site/images/logo-w3c-screen-lg 20140126192558 http://www.w3.org/2008/site/images/logo-w3c-screen-lg warc/revisit - PI67JKISUQ5Z4GNQE63TTYDHM3Y6L4UA - - 646 430746 test.warc.gz +org,w3)/2008/site/images/google 20140126192559 http://www.w3.org/2008/site/images/google warc/revisit - J4XLVFATF4IHPSLUMU2LPXXEUDQYR3PY - - 632 431901 test.warc.gz +org,w3)/2008/site/images/category-bg-fold.png 20140126192600 http://www.w3.org/2008/site/images/category-bg-fold.png warc/revisit - ZK6MO433VCNDIRQYUGWZ2SDDIQFZSCFP - - 593 433032 test.warc.gz +org,w3)/2008/site/images/category-bg.png 20140126192601 http://www.w3.org/2008/site/images/category-bg.png warc/revisit - G6TZMIU3MCYZVEDPMC2DL4M6WLFWHKYA - - 591 434136 test.warc.gz +org,w3)/2008/site/images/skip.png 20140126192601 http://www.w3.org/2008/site/images/skip.png warc/revisit - KYGR5HVCUVP3G2XHITC43CXG4W7IDOW5 - - 583 435233 test.warc.gz +org,w3)/2008/site/images/bct.png 20140126192601 http://www.w3.org/2008/site/images/bct.png warc/revisit - WOQ2FH33THZ2FNKFVPMAOKYJOZW7RXUD - - 582 436319 test.warc.gz +org,w3)/2008/site/images/talks-bg-left.png 20140126192601 http://www.w3.org/2008/site/images/talks-bg-left.png warc/revisit - YUTG7VQMNMX37DIOBPZ5Y5EK66UED3HI - - 594 437401 test.warc.gz +org,w3)/2008/site/images/talks-bg-right.png 20140126192601 http://www.w3.org/2008/site/images/talks-bg-right.png warc/revisit - EVI3SG6LZL46O53T6HGNX6FSXUBD77SE - - 594 438503 test.warc.gz +org,w3)/2008/site/images/talks-bg.png 20140126192601 http://www.w3.org/2008/site/images/talks-bg.png warc/revisit - 3J27MFEO6JE3HTIPYTWIJZBZ5UJUO5EI - - 586 439607 test.warc.gz +org,w3)/2008/site/images/footer-shadow.png 20140126192602 http://www.w3.org/2008/site/images/footer-shadow.png warc/revisit - RC2EPFVZLPHI33BEKZYNE5XZIP5Q6QXL - - 598 440697 test.warc.gz +org,w3)/2008/site/images/ico-minus 20140126192602 http://www.w3.org/2008/site/images/ico-minus warc/revisit - 3W5VMCQOL56ZJ6QP3QL2SMWBETHXCHFN - - 634 441803 test.warc.gz +org,w3)/2008/site/images/twitter-bird 20140126192602 http://www.w3.org/2008/site/images/twitter-bird warc/revisit - 4NMC2Y4ZJVGNHHSVHK4IU2H4QGMODUUD - - 637 442938 test.warc.gz +org,w3)/international/multilingualweb/logo/mlw-logo-lt-124.png 20140126192602 http://www.w3.org/International/multilingualweb/logo/mlw-logo-lt-124.png warc/revisit - ND4CONRUJWIUNYY3PLJVZKYHNKXW3EGZ - - 615 444079 test.warc.gz +org,w3)/2008/site/images/ico-plus 20140126192602 http://www.w3.org/2008/site/images/ico-plus warc/revisit - ZBGPPB5UR7BLPFOJGZSDM7PNBJLECURY - - 632 445215 test.warc.gz +org,iana)/ 20140126192643 http://iana.org unk 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 340 446349 test.warc.gz +org,iana)/ 20140126192644 http://www.iana.org/ warc/revisit - OSSAPWJ23L56IYVRW3GFEAR4MCJMGPTB - - 535 447165 test.warc.gz +org,iana)/_js/2013.1/iana.js 20140126192645 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 458 448183 test.warc.gz +org,iana)/_css/2013.1/print.css 20140126192645 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 543 449119 test.warc.gz +org,iana)/_css/2013.1/screen.css 20140126192645 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 544 450150 test.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126192645 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 551 451182 test.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126192645 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 553 452214 test.warc.gz +org,iana)/_img/2013.1/iana-logo-homepage.png 20140126192645 http://www.iana.org/_img/2013.1/iana-logo-homepage.png warc/revisit - GCW2GM3SIMHEIQYZX25MLSRYVWUCZ7OK - - 552 453259 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126192646 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 559 454309 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126192646 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 543 455360 test.warc.gz +org,iana)/_img/bookmark_icon.ico 20140126192647 http://www.iana.org/_img/bookmark_icon.ico warc/revisit - PG3PAWWE72JQ37CXJSPCJNNF7QI3SNX7 - - 547 456397 test.warc.gz +org,iana)/about 20140126192706 http://iana.org/about/ unk 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 346 457418 test.warc.gz +org,iana)/about 20140126192706 http://www.iana.org/about/ text/html 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 434 458249 test.warc.gz +org,iana)/about 20140126192708 http://www.iana.org/about warc/revisit - 6G77LZKFAVKH4PCWWKMW6TRJPSHWUBI3 - - 535 459172 test.warc.gz +org,iana)/_js/2013.1/iana.js 20140126192708 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 458 460194 test.warc.gz +org,iana)/_css/2013.1/screen.css 20140126192708 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 545 461132 test.warc.gz +org,iana)/_css/2013.1/print.css 20140126192708 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 540 462171 test.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126192708 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 550 463204 test.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126192709 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 537 464239 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126192709 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 560 465277 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126192709 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 545 466333 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126192709 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 557 467375 test.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126192709 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 553 468426 test.warc.gz +org,iana)/numbers 20140126192742 http://www.iana.org/numbers warc/revisit - HWT5UZKURYLW5QNWVZCWFCANGEMU7XWK - - 541 469477 test.warc.gz +org,iana)/_js/2013.1/iana.js 20140126192743 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 453 470505 test.warc.gz +org,iana)/_css/2013.1/print.css 20140126192743 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 540 471438 test.warc.gz +org,iana)/_css/2013.1/screen.css 20140126192743 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 539 472472 test.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126192743 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 547 473507 test.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126192743 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 550 474538 test.warc.gz +org,iana)/_img/2013.1/rir-map.svg 20140126192743 http://www.iana.org/_img/2013.1/rir-map.svg warc/revisit - C4LTM7ATRZYZL3W2UCEEX6A26L6PIT4K - - 544 475590 test.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126192743 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 551 476627 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126192743 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 556 477677 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126192743 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 561 478732 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126192743 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 557 479793 test.warc.gz +org,iana)/protocols 20140126192809 http://iana.org/protocols unk 302 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 348 480847 test.warc.gz +org,iana)/protocols 20140126192809 http://www.iana.org/protocols text/html 200 IRUJZEUAXOUUG224ZMI4VWTUPJX6XJTT - - 63662 481683 test.warc.gz +org,iana)/_js/2013.1/iana.js 20140126192814 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 457 545836 test.warc.gz +org,iana)/_css/2013.1/print.css 20140126192814 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 541 546776 test.warc.gz +org,iana)/_css/2013.1/screen.css 20140126192814 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 539 547812 test.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126192814 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 547 548847 test.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126192814 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 549 549881 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126192815 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 562 550934 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126192815 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 543 551997 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126192815 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 541 553038 test.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126192817 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 551 554077 test.warc.gz +org,iana)/domains 20140126192835 http://www.iana.org/domains warc/revisit - 7UPSCLNWNZP33LGW6OJGSF2Y4CDG4ES7 - - 539 555128 test.warc.gz +org,iana)/_js/2013.1/iana.js 20140126192835 http://www.iana.org/_js/2013.1/iana.js application/x-javascript 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 458 556157 test.warc.gz +org,iana)/_css/2013.1/screen.css 20140126192835 http://www.iana.org/_css/2013.1/screen.css warc/revisit - BUAEPXZNN44AIX3NLXON4QDV6OY2H5QD - - 543 557098 test.warc.gz +org,iana)/_css/2013.1/print.css 20140126192835 http://www.iana.org/_css/2013.1/print.css warc/revisit - VNBXHMUNWJQC5OWWGZ3X7GM5C7X6ZAB4 - - 540 558135 test.warc.gz +org,iana)/_js/2013.1/jquery.js 20140126192835 http://www.iana.org/_js/2013.1/jquery.js warc/revisit - AAW2RS7JB7HTF666XNZDQYJFA6PDQBPO - - 551 559167 test.warc.gz +org,iana)/_img/2013.1/iana-logo-header.svg 20140126192835 http://www.iana.org/_img/2013.1/iana-logo-header.svg warc/revisit - N6T6ZRHLEHKP2675D7JVKDYKVKYKWQ6X - - 551 560203 test.warc.gz +org,iana)/_img/2013.1/icann-logo.svg 20140126192836 http://www.iana.org/_img/2013.1/icann-logo.svg warc/revisit - HGRZHOH73EFQQWBYWBSOIV2UU5JDTSGJ - - 551 561255 test.warc.gz +org,iana)/_css/2013.1/fonts/inconsolata.otf 20140126192836 http://www.iana.org/_css/2013.1/fonts/Inconsolata.otf warc/revisit - LNMEDYOENSOEI5VPADCKL3CB6N3GWXPR - - 555 562305 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-regular.ttf 20140126192836 http://www.iana.org/_css/2013.1/fonts/OpenSans-Regular.ttf warc/revisit - GVSO2C2TMPPVZ4TXYFXAY27NYWTIEIL7 - - 557 563349 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-semibold.ttf 20140126192836 http://www.iana.org/_css/2013.1/fonts/OpenSans-Semibold.ttf warc/revisit - 6HXHVHDNCPXC2ZBKQBWATZZXE5PGCN4S - - 561 564402 test.warc.gz +org,iana)/_css/2013.1/fonts/opensans-bold.ttf 20140126192836 http://www.iana.org/_css/2013.1/fonts/OpenSans-Bold.ttf warc/revisit - YFUR5ALIWJMWV6FAAFRLVRQNXZQF5HRW - - 552 565464 test.warc.gz diff --git a/test/test.warc.gz b/test/test.warc.gz new file mode 100644 index 00000000..06551e1c Binary files /dev/null and b/test/test.warc.gz differ