sanitize_filename,
unescapeHTML,
)
+_NO_DEFAULT = object()
class InfoExtractor(object):
video_info['title'] = playlist_title
return video_info
- def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+ def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
"""
Perform a regex search on the given string, using a single or a list of
patterns returning the first matching group.
if mobj:
# return the first matching group
return next(g for g in mobj.groups() if g is not None)
- elif default is not None:
+ elif default is not _NO_DEFAULT:
return default
elif fatal:
raise RegexNotFoundError(u'Unable to extract %s' % _name)
u'please report this issue on http://yt-dl.org/bug' % _name)
return None
- def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+ def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
"""
Like _search_regex, but strips HTML tags and unescapes entities.
"""
video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, u'title')
video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, u'uploader', fatal=False)
- video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', default=None)
+ video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', fatal=False)
video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, u'video_url').replace('\\/', '/')
path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:]
video_description = u''
def _extract_count(klass):
- count = self._search_regex(r'class="%s">([\d,]+)</span>' % re.escape(klass), video_webpage, klass, fatal=False)
+ count = self._search_regex(
+ r'class="%s">([\d,]+)</span>' % re.escape(klass),
+ video_webpage, klass, default=None)
if count is not None:
return int(count.replace(',', ''))
return None