[subtitles] refactor to support websites with subtitle information the

webpage.

I added the parameter webpage, so now it's similar to the way automatic
captions are handled. This is an improvement needed for websites like
TED.
This commit is contained in:
Ismaël Mejía 2013-11-02 18:01:05 +01:00
parent c45aa56080
commit 1f343eaabb
3 changed files with 10 additions and 10 deletions

View file

@ -113,9 +113,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
video_url = info[max_quality] video_url = info[max_quality]
# subtitles # subtitles
video_subtitles = self.extract_subtitles(video_id) video_subtitles = self.extract_subtitles(video_id, webpage)
if self._downloader.params.get('listsubtitles', False): if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(video_id) self._list_available_subtitles(video_id, webpage)
return return
return [{ return [{
@ -129,7 +129,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
'thumbnail': info['thumbnail_url'] 'thumbnail': info['thumbnail_url']
}] }]
def _get_available_subtitles(self, video_id): def _get_available_subtitles(self, video_id, webpage):
try: try:
sub_list = self._download_webpage( sub_list = self._download_webpage(
'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,

View file

@ -12,9 +12,9 @@ class SubtitlesInfoExtractor(InfoExtractor):
return any([self._downloader.params.get('writesubtitles', False), return any([self._downloader.params.get('writesubtitles', False),
self._downloader.params.get('writeautomaticsub')]) self._downloader.params.get('writeautomaticsub')])
def _list_available_subtitles(self, video_id, webpage=None): def _list_available_subtitles(self, video_id, webpage):
""" outputs the available subtitles for the video """ """ outputs the available subtitles for the video """
sub_lang_list = self._get_available_subtitles(video_id) sub_lang_list = self._get_available_subtitles(video_id, webpage)
auto_captions_list = self._get_available_automatic_caption(video_id, webpage) auto_captions_list = self._get_available_automatic_caption(video_id, webpage)
sub_lang = ",".join(list(sub_lang_list.keys())) sub_lang = ",".join(list(sub_lang_list.keys()))
self.to_screen(u'%s: Available subtitles for video: %s' % self.to_screen(u'%s: Available subtitles for video: %s' %
@ -23,7 +23,7 @@ class SubtitlesInfoExtractor(InfoExtractor):
self.to_screen(u'%s: Available automatic captions for video: %s' % self.to_screen(u'%s: Available automatic captions for video: %s' %
(video_id, auto_lang)) (video_id, auto_lang))
def extract_subtitles(self, video_id, video_webpage=None): def extract_subtitles(self, video_id, webpage):
""" """
returns {sub_lang: sub} ,{} if subtitles not found or None if the returns {sub_lang: sub} ,{} if subtitles not found or None if the
subtitles aren't requested. subtitles aren't requested.
@ -32,9 +32,9 @@ class SubtitlesInfoExtractor(InfoExtractor):
return None return None
available_subs_list = {} available_subs_list = {}
if self._downloader.params.get('writeautomaticsub', False): if self._downloader.params.get('writeautomaticsub', False):
available_subs_list.update(self._get_available_automatic_caption(video_id, video_webpage)) available_subs_list.update(self._get_available_automatic_caption(video_id, webpage))
if self._downloader.params.get('writesubtitles', False): if self._downloader.params.get('writesubtitles', False):
available_subs_list.update(self._get_available_subtitles(video_id)) available_subs_list.update(self._get_available_subtitles(video_id, webpage))
if not available_subs_list: # error, it didn't get the available subtitles if not available_subs_list: # error, it didn't get the available subtitles
return {} return {}
@ -74,7 +74,7 @@ class SubtitlesInfoExtractor(InfoExtractor):
return return
return sub return sub
def _get_available_subtitles(self, video_id): def _get_available_subtitles(self, video_id, webpage):
""" """
returns {sub_lang: url} or {} if not available returns {sub_lang: url} or {} if not available
Must be redefined by the subclasses Must be redefined by the subclasses

View file

@ -1099,7 +1099,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
else: else:
raise ExtractorError(u'Unable to decrypt signature, key length %d not supported; retrying might work' % (len(s))) raise ExtractorError(u'Unable to decrypt signature, key length %d not supported; retrying might work' % (len(s)))
def _get_available_subtitles(self, video_id): def _get_available_subtitles(self, video_id, webpage):
try: try:
sub_list = self._download_webpage( sub_list = self._download_webpage(
'http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, 'http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,