Merge branch 'master' into subtitles_rework

[youtube-dl] / youtube_dl / extractor / common.py

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 05b24387165fd5678cd77a7e37918bb2ce354d51..52c4483c9ecafe914270444b848ba8ac5966f802 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -14,6 +14,7 @@ from ..utils import (
     clean_html,
     compiled_regex_type,
     ExtractorError,
+    unescapeHTML,
 )
 
 class InfoExtractor(object):
@@ -46,7 +47,8 @@ class InfoExtractor(object):
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
     player_url:     SWF Player URL (used for rtmpdump).
-    subtitles:      The subtitle file contents.
+    subtitles:      The subtitle file contents as a dictionary in the format
+                    {language: subtitles}.
     view_count:     How many users have watched the video on the platform.
     urlhandle:      [internal] The urlHandle to be used to download the file,
                     like returned by urllib.request.urlopen
@@ -76,7 +78,13 @@ class InfoExtractor(object):
     @classmethod
     def suitable(cls, url):
         """Receives a URL and returns True if suitable for this IE."""
-        return re.match(cls._VALID_URL, url) is not None
+
+        # This does not use has/getattr intentionally - we want to know whether
+        # we have cached the regexp for *this* class, whereas getattr would also
+        # match the superclass
+        if '_VALID_URL_RE' not in cls.__dict__:
+            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+        return cls._VALID_URL_RE.match(url) is not None
 
     @classmethod
     def working(cls):
@@ -125,6 +133,11 @@ 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)
@@ -259,16 +272,17 @@ class InfoExtractor(object):
 
     # Helper functions for extracting OpenGraph info
     @staticmethod
-    def _og_regex(property):
-        return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % property
+    def _og_regex(prop):
+        return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % re.escape(prop)
 
-    def _og_search_property(self, property, html, name=None, **kargs):
+    def _og_search_property(self, prop, html, name=None, **kargs):
         if name is None:
-            name = 'OpenGraph %s' % property
-        return self._html_search_regex(self._og_regex(property), html, name, flags=re.DOTALL, **kargs)
+            name = 'OpenGraph %s' % prop
+        escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+        return unescapeHTML(escaped)
 
     def _og_search_thumbnail(self, html, **kargs):
-        return self._og_search_property('image', html, 'thumbnail url', fatal=False, **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)