diff options
Diffstat (limited to 'youtube_dl/extractor/common.py')
| -rw-r--r-- | youtube_dl/extractor/common.py | 29 |
1 files changed, 29 insertions, 0 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 1bd5538ca..ec988fc90 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -125,6 +125,11 @@ class InfoExtractor(object): def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): """ Returns a tuple (page content as string, URL handle) """ + + # Strip hashes from the URL (#1038) + if isinstance(url_or_request, (compat_str, str)): + url_or_request = url_or_request.partition('#')[0] + urlh = self._request_webpage(url_or_request, video_id, note, errnote) content_type = urlh.headers.get('Content-Type', '') m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) @@ -257,6 +262,30 @@ class InfoExtractor(object): return (username, password) + # Helper functions for extracting OpenGraph info + @staticmethod + def _og_regex(prop): + return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % re.escape(prop) + + def _og_search_property(self, prop, html, name=None, **kargs): + if name is None: + name = 'OpenGraph %s' % prop + return self._html_search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs) + + def _og_search_thumbnail(self, html, **kargs): + return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs) + + def _og_search_description(self, html, **kargs): + return self._og_search_property('description', html, fatal=False, **kargs) + + def _og_search_title(self, html, **kargs): + return self._og_search_property('title', html, **kargs) + + def _og_search_video_url(self, html, name='video url', **kargs): + return self._html_search_regex([self._og_regex('video:secure_url'), + self._og_regex('video')], + html, name, **kargs) + class SearchInfoExtractor(InfoExtractor): """ Base class for paged search queries extractors. |