From 8377574c9cb8740e24d45e9b3d30921fd6ec846c Mon Sep 17 00:00:00 2001 From: Ismael Mejia Date: Thu, 8 Aug 2013 08:54:10 +0200 Subject: [PATCH] [internal] Improved subtitle architecture + (update in youtube/dailymotion) The structure of subtitles was refined, you only need to implement one method that returns a dictionnary of the available subtitles (lang, url) to support all the subtitle options in a website. I updated the subtitle downloaders for youtube/dailymotion to show how it works. --- youtube_dl/extractor/dailymotion.py | 15 +-- youtube_dl/extractor/subtitles.py | 27 ++--- youtube_dl/extractor/youtube.py | 175 ++++++++++------------------ 3 files changed, 73 insertions(+), 144 deletions(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index eb2322d54..97003ee35 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,6 +1,5 @@ import re import json -import itertools import socket from .common import InfoExtractor @@ -34,16 +33,12 @@ class DailyMotionSubtitlesIE(SubtitlesIE): self._downloader.report_warning(u'video doesn\'t have subtitles') return {} - def _get_subtitle_url(self, sub_lang, sub_name, video_id, format): - sub_lang_list = self._get_available_subtitles(video_id) - return sub_lang_list[sub_lang] - def _request_automatic_caption(self, video_id, webpage): - self._downloader.report_warning(u'Automatic Captions not supported by dailymotion') + self._downloader.report_warning(u'Automatic Captions not supported by this server') return {} -class DailymotionIE(DailyMotionSubtitlesIE): #,InfoExtractor): +class DailymotionIE(DailyMotionSubtitlesIE): """Information Extractor for Dailymotion""" _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' @@ -116,12 +111,6 @@ class DailymotionIE(DailyMotionSubtitlesIE): #,InfoExtractor): self._list_available_subtitles(video_id) return - if 'length_seconds' not in info: - self._downloader.report_warning(u'unable to extract video duration') - video_duration = '' - else: - video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) - return [{ 'id': video_id, 'url': video_url, diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py index 89864e5d7..8843e0220 100644 --- a/youtube_dl/extractor/subtitles.py +++ b/youtube_dl/extractor/subtitles.py @@ -15,7 +15,8 @@ class SubtitlesIE(InfoExtractor): def report_video_subtitles_available(self, video_id, sub_lang_list): """Report available subtitles.""" sub_lang = ",".join(list(sub_lang_list.keys())) - self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang)) + self.to_screen(u'%s: Available subtitles for video: %s' % + (video_id, sub_lang)) def _list_available_subtitles(self, video_id): sub_lang_list = self._get_available_subtitles(video_id) @@ -27,9 +28,9 @@ class SubtitlesIE(InfoExtractor): couldn't be found """ sub_lang_list = self._get_available_subtitles(video_id) - sub_format = self._downloader.params.get('subtitlesformat') - if not sub_lang_list: #There was some error, it didn't get the available subtitles + if not sub_lang_list: # error, it didn't get the available subtitles return {} + if self._downloader.params.get('writesubtitles', False): if self._downloader.params.get('subtitleslang', False): sub_lang = self._downloader.params.get('subtitleslang') @@ -41,18 +42,15 @@ class SubtitlesIE(InfoExtractor): self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang) return {} sub_lang_list = {sub_lang: sub_lang_list[sub_lang]} + subtitles = {} - for sub_lang in sub_lang_list: - subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) + for sub_lang, url in sub_lang_list.iteritems(): + subtitle = self._request_subtitle_url(sub_lang, url) if subtitle: subtitles[sub_lang] = subtitle return subtitles - def _request_subtitle(self, sub_lang, sub_name, video_id, format): - """ Return the subtitle as a string or None if they are not found """ - # return (u'Did not fetch video subtitles for %s' % sub_lang, None, None) - self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) - url = self._get_subtitle_url(sub_lang, sub_name, video_id, format) + def _request_subtitle_url(self, sub_lang, url): try: sub = compat_urllib_request.urlopen(url).read().decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -64,13 +62,8 @@ class SubtitlesIE(InfoExtractor): return sub def _get_available_subtitles(self, video_id): - """Get available subtitles. Redefine in subclasses.""" - """returns {(lang, url)} """ - # return {} - pass - - def _get_subtitle_url(self, sub_lang, sub_name, video_id, format): - """returns the url for the given subtitle. Redefine in subclasses.""" + """returns the list of available subtitles like this {lang: url} """ + """or {} if not available. Must be redefined by the subclasses.""" pass def _request_automatic_caption(self, video_id, webpage): diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 2b03226f6..414e33b49 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -7,6 +7,7 @@ import socket import itertools from .common import InfoExtractor, SearchInfoExtractor +from .subtitles import SubtitlesIE from ..utils import ( compat_http_client, compat_parse_qs, @@ -24,7 +25,66 @@ from ..utils import ( ) -class YoutubeIE(InfoExtractor): +class YoutubeSubtitlesIE(SubtitlesIE): + + def _get_available_subtitles(self, video_id): + request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) + try: + sub_list = compat_urllib_request.urlopen(request).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: %s' % compat_str(err)) + return {} + lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) + + sub_lang_list = {} + for l in lang_list: + lang = l[1] + params = compat_urllib_parse.urlencode({ + 'lang': lang, + 'v': video_id, + 'fmt': self._downloader.params.get('subtitlesformat'), + }) + url = u'http://www.youtube.com/api/timedtext?' + params + sub_lang_list[lang] = url + if not sub_lang_list: + self._downloader.report_warning(u'video doesn\'t have subtitles') + return {} + return sub_lang_list + + def _request_automatic_caption(self, video_id, webpage): + """We need the webpage for getting the captions url, pass it as an + argument to speed up the process.""" + sub_lang = self._downloader.params.get('subtitleslang') or 'en' + sub_format = self._downloader.params.get('subtitlesformat') + self.to_screen(u'%s: Looking for automatic captions' % video_id) + mobj = re.search(r';ytplayer.config = ({.*?});', webpage) + err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang + if mobj is None: + self._downloader.report_warning(err_msg) + return {} + player_config = json.loads(mobj.group(1)) + try: + args = player_config[u'args'] + caption_url = args[u'ttsurl'] + timestamp = args[u'timestamp'] + params = compat_urllib_parse.urlencode({ + 'lang': 'en', + 'tlang': sub_lang, + 'fmt': sub_format, + 'ts': timestamp, + 'kind': 'asr', + }) + subtitles_url = caption_url + '&' + params + sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions') + return {sub_lang: sub} + # An extractor error can be raise by the download process if there are + # no automatic captions but there are subtitles + except (KeyError, ExtractorError): + self._downloader.report_warning(err_msg) + return {} + + +class YoutubeIE(YoutubeSubtitlesIE): IE_DESC = u'YouTube.com' _VALID_URL = r"""^ ( @@ -151,19 +211,6 @@ class YoutubeIE(InfoExtractor): """Report attempt to download video info webpage.""" self.to_screen(u'%s: Downloading video info webpage' % video_id) - def report_video_subtitles_download(self, video_id): - """Report attempt to download video info webpage.""" - self.to_screen(u'%s: Checking available subtitles' % video_id) - - def report_video_subtitles_request(self, video_id, sub_lang, format): - """Report attempt to download video info webpage.""" - self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) - - def report_video_subtitles_available(self, video_id, sub_lang_list): - """Report available subtitles.""" - sub_lang = ",".join(list(sub_lang_list.keys())) - self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang)) - def report_information_extraction(self, video_id): """Report attempt to extract video information.""" self.to_screen(u'%s: Extracting video information' % video_id) @@ -203,106 +250,6 @@ class YoutubeIE(InfoExtractor): else: raise ExtractorError(u'Unable to decrypt signature, key length %d not supported; retrying might work' % (len(s))) - def _get_available_subtitles(self, video_id): - self.report_video_subtitles_download(video_id) - request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) - try: - sub_list = compat_urllib_request.urlopen(request).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: %s' % compat_str(err)) - return {} - sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) - sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list) - if not sub_lang_list: - self._downloader.report_warning(u'video doesn\'t have subtitles') - return {} - return sub_lang_list - - def _list_available_subtitles(self, video_id): - sub_lang_list = self._get_available_subtitles(video_id) - self.report_video_subtitles_available(video_id, sub_lang_list) - - def _request_subtitle(self, sub_lang, sub_name, video_id, format): - """ - Return the subtitle as a string or None if they are not found - """ - self.report_video_subtitles_request(video_id, sub_lang, format) - params = compat_urllib_parse.urlencode({ - 'lang': sub_lang, - 'name': sub_name, - 'v': video_id, - 'fmt': format, - }) - url = 'http://www.youtube.com/api/timedtext?' + params - 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))) - return - if not sub: - self._downloader.report_warning(u'Did not fetch video subtitles') - return - return sub - - def _request_automatic_caption(self, video_id, webpage): - """We need the webpage for getting the captions url, pass it as an - argument to speed up the process.""" - sub_lang = self._downloader.params.get('subtitleslang') or 'en' - sub_format = self._downloader.params.get('subtitlesformat') - self.to_screen(u'%s: Looking for automatic captions' % video_id) - mobj = re.search(r';ytplayer.config = ({.*?});', webpage) - err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang - if mobj is None: - self._downloader.report_warning(err_msg) - return {} - player_config = json.loads(mobj.group(1)) - try: - args = player_config[u'args'] - caption_url = args[u'ttsurl'] - timestamp = args[u'timestamp'] - params = compat_urllib_parse.urlencode({ - 'lang': 'en', - 'tlang': sub_lang, - 'fmt': sub_format, - 'ts': timestamp, - 'kind': 'asr', - }) - subtitles_url = caption_url + '&' + params - sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions') - return {sub_lang: sub} - # An extractor error can be raise by the download process if there are - # no automatic captions but there are subtitles - except (KeyError, ExtractorError): - self._downloader.report_warning(err_msg) - return {} - - def _extract_subtitles(self, video_id): - """ - Return a dictionary: {language: subtitles} or {} if the subtitles - couldn't be found - """ - sub_lang_list = self._get_available_subtitles(video_id) - sub_format = self._downloader.params.get('subtitlesformat') - if not sub_lang_list: #There was some error, it didn't get the available subtitles - return {} - if self._downloader.params.get('writesubtitles', False): - if self._downloader.params.get('subtitleslang', False): - sub_lang = self._downloader.params.get('subtitleslang') - elif 'en' in sub_lang_list: - sub_lang = 'en' - else: - sub_lang = list(sub_lang_list.keys())[0] - if not sub_lang in sub_lang_list: - self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang) - return {} - sub_lang_list = {sub_lang: sub_lang_list[sub_lang]} - subtitles = {} - for sub_lang in sub_lang_list: - subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) - if subtitle: - subtitles[sub_lang] = subtitle - return subtitles - def _print_formats(self, formats): print('Available formats:') for x in formats: