X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsubtitles.py;h=59a51268d25ed4b0718c67ae91a5e8f07fcfe42c;hb=1b40dc92eb27b2a3f299157f83bfc8e95ca42268;hp=c10cdf266737737d5c0d985c9e29e3bac1c8399d;hpb=d6e203b3dcef8f291b57021903e629d3e30e1f0b;p=youtube-dl diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py index c10cdf266..59a51268d 100644 --- a/youtube_dl/extractor/subtitles.py +++ b/youtube_dl/extractor/subtitles.py @@ -1,46 +1,60 @@ -import socket - +from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - compat_http_client, - compat_urllib_error, - compat_urllib_request, - compat_str, + ExtractorError, ) -class SubtitlesIE(InfoExtractor): +class SubtitlesInfoExtractor(InfoExtractor): + @property + def _have_to_download_any_subtitles(self): + return any([self._downloader.params.get('writesubtitles', False), + self._downloader.params.get('writeautomaticsub')]) - def _list_available_subtitles(self, video_id): + def _list_available_subtitles(self, video_id, webpage): """ 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) sub_lang = ",".join(list(sub_lang_list.keys())) - self.to_screen(u'%s: Available subtitles for video: %s' % + self.to_screen('%s: Available subtitles for video: %s' % (video_id, sub_lang)) + auto_lang = ",".join(auto_captions_list.keys()) + self.to_screen('%s: Available automatic captions for video: %s' % + (video_id, auto_lang)) + + def extract_subtitles(self, video_id, webpage): + """ + returns {sub_lang: sub} ,{} if subtitles not found or None if the + subtitles aren't requested. + """ + if not self._have_to_download_any_subtitles: + return None + available_subs_list = {} + if self._downloader.params.get('writeautomaticsub', False): + available_subs_list.update(self._get_available_automatic_caption(video_id, webpage)) + if self._downloader.params.get('writesubtitles', False): + available_subs_list.update(self._get_available_subtitles(video_id, webpage)) - def _extract_subtitles(self, video_id): - """ returns {sub_lang: sub} or {} if subtitles not found """ - available_subs_list = self._get_available_subtitles(video_id) if not available_subs_list: # error, it didn't get the available subtitles return {} if self._downloader.params.get('allsubtitles', False): sub_lang_list = available_subs_list else: - if self._downloader.params.get('writesubtitles', False): - if self._downloader.params.get('subtitleslangs', False): - requested_langs = self._downloader.params.get('subtitleslangs') - elif 'en' in available_subs_list: - requested_langs = ['en'] - else: - requested_langs = [list(available_subs_list.keys())[0]] + if self._downloader.params.get('subtitleslangs', False): + requested_langs = self._downloader.params.get('subtitleslangs') + elif 'en' in available_subs_list: + requested_langs = ['en'] + else: + requested_langs = [list(available_subs_list.keys())[0]] - sub_lang_list = {} - for sub_lang in requested_langs: - if not sub_lang in available_subs_list: - self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang) - continue - sub_lang_list[sub_lang] = available_subs_list[sub_lang] + sub_lang_list = {} + for sub_lang in requested_langs: + if sub_lang not in available_subs_list: + self._downloader.report_warning('no closed captions found in the specified language "%s"' % sub_lang) + continue + sub_lang_list[sub_lang] = available_subs_list[sub_lang] subtitles = {} for sub_lang, url in sub_lang_list.items(): @@ -49,32 +63,37 @@ class SubtitlesIE(InfoExtractor): subtitles[sub_lang] = subtitle return subtitles + def _download_subtitle_url(self, sub_lang, url): + return self._download_webpage(url, None, note=False) + def _request_subtitle_url(self, sub_lang, url): """ makes the http request for the subtitle """ try: - sub = compat_urllib_request.urlopen(url).read().decode('utf-8') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err))) + sub = self._download_subtitle_url(sub_lang, url) + except ExtractorError as err: + self._downloader.report_warning('unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err))) return if not sub: - self._downloader.report_warning(u'Did not fetch video subtitles') + self._downloader.report_warning('Did not fetch video subtitles') return return sub - def _get_available_subtitles(self, video_id): - """ returns {sub_lang: url} or {} if not available """ - """ Must be redefined by the subclasses """ - pass - - def _request_automatic_caption(self, video_id, webpage): - """ returns {sub_lang: sub} or {} if not available """ - """ Must be redefined by the subclasses """ - pass - + def _get_available_subtitles(self, video_id, webpage): + """ + returns {sub_lang: url} or {} if not available + Must be redefined by the subclasses + """ -class NoAutoSubtitlesIE(SubtitlesIE): - """ A subtitle class for the servers that don't support auto-captions""" + # By default, allow implementations to simply pass in the result + assert isinstance(webpage, dict), \ + '_get_available_subtitles not implemented' + return webpage - def _request_automatic_caption(self, video_id, webpage): - self._downloader.report_warning(u'Automatic Captions not supported by this server') + def _get_available_automatic_caption(self, video_id, webpage): + """ + returns {sub_lang: url} or {} if not available + Must be redefined by the subclasses that support automatic captions, + otherwise it will return {} + """ + self._downloader.report_warning('Automatic Captions not supported by this server') return {}