diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 1fc0624a3..939249d7b 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -18,6 +18,7 @@ sanitize_filename, unescapeHTML, ) +_NO_DEFAULT = object() class InfoExtractor(object): @@ -281,7 +282,7 @@ def playlist_result(self, entries, playlist_id=None, playlist_title=None): 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. @@ -303,7 +304,7 @@ def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0 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) @@ -312,7 +313,7 @@ def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0 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. """ diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index e3458d2bd..1a6a7688d 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -32,7 +32,7 @@ def _real_extract(self, url): video_title = self._html_search_regex(r'
([^<]+)', 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:] diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index a68a214ca..c860eedda 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1361,7 +1361,9 @@ def _real_extract(self, url): video_description = u'' def _extract_count(klass): - count = self._search_regex(r'class="%s">([\d,]+)' % re.escape(klass), video_webpage, klass, fatal=False) + count = self._search_regex( + r'class="%s">([\d,]+)' % re.escape(klass), + video_webpage, klass, default=None) if count is not None: return int(count.replace(',', '')) return None