X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcommon.py;h=b77f0e51904d1539a43c056dafbc82a587041744;hb=cad985ab4d78ef00a77932e87cee5aba8a1e3320;hp=7e4113213c8a850f42b58e187e69870d81102d43;hpb=2c8e03d937cc08d0d924b24a95fcc2eb3076e544;p=youtube-dl.git
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 7e4113213..b77f0e519 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -12,13 +12,14 @@ import sys
import time
import xml.etree.ElementTree
-from ..utils import (
+from ..compat import (
compat_http_client,
compat_urllib_error,
compat_urllib_parse_urlparse,
compat_urlparse,
compat_str,
-
+)
+from ..utils import (
clean_html,
compiled_regex_type,
ExtractorError,
@@ -403,7 +404,7 @@ class InfoExtractor(object):
video_info['title'] = playlist_title
return video_info
- def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
+ def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
"""
Perform a regex search on the given string, using a single or a list of
patterns returning the first matching group.
@@ -424,8 +425,11 @@ class InfoExtractor(object):
_name = name
if mobj:
- # return the first matching group
- return next(g for g in mobj.groups() if g is not None)
+ if group is None:
+ # return the first matching group
+ return next(g for g in mobj.groups() if g is not None)
+ else:
+ return mobj.group(group)
elif default is not _NO_DEFAULT:
return default
elif fatal:
@@ -435,11 +439,11 @@ class InfoExtractor(object):
'please report this issue on http://yt-dl.org/bug' % _name)
return None
- def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
+ def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
"""
Like _search_regex, but strips HTML tags and unescapes entities.
"""
- res = self._search_regex(pattern, string, name, default, fatal, flags)
+ res = self._search_regex(pattern, string, name, default, fatal, flags, group)
if res:
return clean_html(res).strip()
else:
@@ -533,9 +537,9 @@ class InfoExtractor(object):
display_name = name
return self._html_search_regex(
r'''(?ix)]+(?:itemprop|name|property)=["\']?%s["\']?)
- [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
- html, display_name, fatal=fatal, **kwargs)
+ (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
+ [^>]+content=(["\'])(?P.*?)\1''' % re.escape(name),
+ html, display_name, fatal=fatal, group='content', **kwargs)
def _dc_search_uploader(self, html):
return self._html_search_meta('dc.creator', html, 'uploader')