backup/warcprox
1
0
Fork 0
mirror of https://github.com/internetarchive/warcprox.git synced 2025-01-18 13:22:09 +01:00
Code Issues Projects Releases Activity

fixes to let screenshot recordss be saved in big capture tables for wayback playback

Browse Source
This commit is contained in:
Noah Levitt 2015-09-07 06:15:15 +00:00
parent c02c98e369
commit 686a297f98
2 changed files with 14 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
warcprox/bigtable.py
View File

@ -11,6 +11,7 @@ import warcprox
import base64 import base64
import surt import surt
import os import os
import hashlib
class RethinkCaptures: class RethinkCaptures:
logger = logging.getLogger("warcprox.bigtables.RethinkCaptures") logger = logging.getLogger("warcprox.bigtables.RethinkCaptures")
@ -51,11 +52,14 @@ class RethinkCaptures:
return result return result
def notify(self, recorded_url, records): def notify(self, recorded_url, records):
if not recorded_url.response_recorder: if recorded_url.response_recorder:
return if recorded_url.response_recorder.payload_digest.name == "sha1":
sha1base32 = base64.b32encode(recorded_url.response_recorder.payload_digest.digest()).decode("utf-8")
if recorded_url.response_recorder.payload_digest.name != "sha1": else:
self.logger.warn("digest type is %s but big capture table is indexed by sha1", recorded_url.response_recorder.payload_digest.name) self.logger.warn("digest type is %s but big capture table is indexed by sha1", recorded_url.response_recorder.payload_digest.name)
else:
digest = hashlib.new("sha1", records[0].content[1])
sha1base32 = base64.b32encode(digest.digest()).decode("utf-8")
if recorded_url.warcprox_meta and "captures-bucket" in recorded_url.warcprox_meta: if recorded_url.warcprox_meta and "captures-bucket" in recorded_url.warcprox_meta:
bucket = recorded_url.warcprox_meta["captures-bucket"] bucket = recorded_url.warcprox_meta["captures-bucket"]
@ -75,7 +79,7 @@ class RethinkCaptures:
"filename": os.path.basename(records[0].warc_filename), "filename": os.path.basename(records[0].warc_filename),
"warc_type": records[0].type.decode("utf-8"), "warc_type": records[0].type.decode("utf-8"),
"warc_id": records[0].id.decode("utf-8"), "warc_id": records[0].id.decode("utf-8"),
"sha1base32": base64.b32encode(recorded_url.response_recorder.payload_digest.digest()).decode("utf-8"), "sha1base32": sha1base32,
"content_type": recorded_url.mimetype, "content_type": recorded_url.mimetype,
"response_code": recorded_url.status, "response_code": recorded_url.status,
"http_method": recorded_url.method, "http_method": recorded_url.method,

6
warcprox/warc.py
View File

@ -113,9 +113,11 @@ class WarcRecordBuilder:
else: else:
headers.append((warctools.WarcRecord.CONTENT_LENGTH, str(len(data)).encode('latin1'))) headers.append((warctools.WarcRecord.CONTENT_LENGTH, str(len(data)).encode('latin1')))
block_digest = hashlib.new(self.digest_algorithm, data) digest = hashlib.new(self.digest_algorithm, data)
headers.append((warctools.WarcRecord.BLOCK_DIGEST, headers.append((warctools.WarcRecord.BLOCK_DIGEST,
warcprox.digest_str(block_digest, self.base32))) warcprox.digest_str(digest, self.base32)))
headers.append((warctools.WarcRecord.PAYLOAD_DIGEST,
warcprox.digest_str(digest, self.base32)))
content_tuple = content_type, data content_tuple = content_type, data
record = warctools.WarcRecord(headers=headers, content=content_tuple) record = warctools.WarcRecord(headers=headers, content=content_tuple)