backup/pywb
1
0
Fork 0
mirror of https://github.com/webrecorder/pywb.git synced 2025-03-24 06:59:52 +01:00
Code Issues Projects Releases Activity

lxml: ensure lxml support is optional: if not available,

Browse Source 
use_lxml_parser() will return false and doctests/pytest collection
won't test the lxml parser
This commit is contained in:
Ilya Kreymer 2014-03-26 14:05:02 -07:00
parent 4e53c2e9d8
commit da0623fbbb
3 changed files with 26 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
pywb/rewrite/lxml_html_rewriter.py
View File

@ -1,4 +1,10 @@
import lxml.etree try:
import lxml.etree
LXML_SUPPORTED = True
except ImportError:
LXML_SUPPORTED = False
pass
import cgi import cgi
import re import re

13
pywb/rewrite/rewriterules.py
View File

@ -13,14 +13,17 @@ HTML = HTMLRewriter
#================================================================= #=================================================================
def use_lxml_parser(): def use_lxml_parser():
try: import logging
import logging from lxml_html_rewriter import LXMLHTMLRewriter, LXML_SUPPORTED
from lxml_html_rewriter import LXMLHTMLRewriter
if LXML_SUPPORTED:
global HTML global HTML
HTML = LXMLHTMLRewriter HTML = LXMLHTMLRewriter
logging.debug('Using LXML Parser') logging.debug('Using LXML Parser')
except ImportError: return True
logging.debug('Error Loading LXML Parser') else:
logging.debug('LXML Parser not available')
return False
#================================================================= #=================================================================

17
pywb/rewrite/test/test_lxml_html_rewriter.py
View File

@ -114,10 +114,7 @@ ur"""
from pywb.rewrite.url_rewriter import UrlRewriter from pywb.rewrite.url_rewriter import UrlRewriter
try: from pywb.rewrite.lxml_html_rewriter import LXMLHTMLRewriter, LXML_SUPPORTED
from pywb.rewrite.lxml_html_rewriter import LXMLHTMLRewriter
except ImportError:
pass
urlrewriter = UrlRewriter('20131226101010/http://example.com/some/path/index.html', '/web/') urlrewriter = UrlRewriter('20131226101010/http://example.com/some/path/index.html', '/web/')
@ -127,5 +124,13 @@ def parse(data, head_insert=None):
print parser.rewrite(data) + parser.close() print parser.rewrite(data) + parser.close()
if __name__ == "__main__": if __name__ == "__main__":
import doctest if LXML_SUPPORTED:
doctest.testmod() import doctest
doctest.testmod()
else:
# skip if not supported and lxml not available
if not LXML_SUPPORTED:
import pytest
lxml = pytest.importorskip('lxml.etree')