From 360e1ca5ccabcb5d48228d9472b09f1bce68bbc4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Mon, 16 Feb 2015 21:44:17 +0100 Subject: [PATCH] [youtube] Convert to new subtitles system The automatic captions are stored in the 'automactic_captions' field, which is used if no normal subtitles are found for an specific language. --- test/test_subtitles.py | 5 --- youtube_dl/YoutubeDL.py | 24 ++++++++++---- youtube_dl/extractor/common.py | 12 +++++++ youtube_dl/extractor/youtube.py | 57 ++++++++++++++++++--------------- 4 files changed, 61 insertions(+), 37 deletions(-) diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 84ae0e714..91cebce28 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -50,11 +50,6 @@ class TestYoutubeSubtitles(BaseTestSubtitles): url = 'QRS8MkLhQmM' IE = YoutubeIE - def test_youtube_no_writesubtitles(self): - self.DL.params['writesubtitles'] = False - subtitles = self.getSubtitles() - self.assertEqual(subtitles, None) - def test_youtube_subtitles(self): self.DL.params['writesubtitles'] = True subtitles = self.getSubtitles() diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 8545dc9e9..a47f8f5de 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1020,9 +1020,13 @@ class YoutubeDL(object): info_dict['upload_date'] = upload_date.strftime('%Y%m%d') if self.params.get('listsubtitles', False): - self.list_subtitles(info_dict['id'], info_dict.get('subtitles')) + if 'automatic_captions' in info_dict: + self.list_subtitles(info_dict['id'], info_dict.get('automatic_captions'), 'automatic captions') + self.list_subtitles(info_dict['id'], info_dict.get('subtitles'), 'subtitles') return - info_dict['requested_subtitles'] = self.process_subtitles(info_dict['id'], info_dict.get('subtitles')) + info_dict['requested_subtitles'] = self.process_subtitles( + info_dict['id'], info_dict.get('subtitles'), + info_dict.get('automatic_captions')) # This extractors handle format selection themselves if info_dict['extractor'] in ['Youku']: @@ -1152,8 +1156,14 @@ class YoutubeDL(object): info_dict.update(formats_to_download[-1]) return info_dict - def process_subtitles(self, video_id, available_subs): + def process_subtitles(self, video_id, available_subs, available_autocaps): """Select the requested subtitles and their format""" + if available_autocaps and self.params.get('writeautomaticsub'): + available_subs = available_subs.copy() + for lang, cap_info in available_autocaps.items(): + if lang not in available_subs: + available_subs[lang] = cap_info + if not available_subs: return available_subs @@ -1645,17 +1655,17 @@ class YoutubeDL(object): ['ID', 'width', 'height', 'URL'], [[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails])) - def list_subtitles(self, video_id, subtitles): + def list_subtitles(self, video_id, subtitles, name='subtitles'): if not subtitles: - self.to_screen('%s has no subtitles' % video_id) + self.to_screen('%s has no %s' % (video_id, name)) return header_line = 'Language formats' sub_lines = [ '%-12s%s' % (lang, ', '.join(f['ext'] for f in reversed(formats))) for lang, formats in subtitles.items()] self.to_screen( - 'Available subtitles for %s:\n%s\n%s' % - (video_id, header_line, '\n'.join(sub_lines))) + 'Available %s for %s:\n%s\n%s' % + (name, video_id, header_line, '\n'.join(sub_lines))) def urlopen(self, req): """ Start an HTTP download """ diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index d149e0f92..fe7d8dbc9 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -157,6 +157,8 @@ class InfoExtractor(object): with the "ext" entry and one of: * "data": The subtitles file contents * "url": A url pointing to the subtitles file + automatic_captions: Like 'subtitles', used by the YoutubeIE for + automatically generated captions duration: Length of the video in seconds, as an integer. view_count: How many users have watched the video on the platform. like_count: Number of positive ratings of the video @@ -1007,6 +1009,16 @@ class InfoExtractor(object): def _get_subtitles(self, *args, **kwargs): raise NotImplementedError("This method must be implemented by subclasses") + def extract_automatic_captions(self, *args, **kwargs): + automatic_captions = {} + list_subtitles = self._downloader.params.get('listsubtitles') + if self._downloader.params.get('writeautomaticsub', False) or list_subtitles: + automatic_captions.update(self._get_automatic_captions(*args, **kwargs)) + return automatic_captions + + def _get_automatic_captions(self, *args, **kwargs): + raise NotImplementedError("This method must be implemented by subclasses") + class SearchInfoExtractor(InfoExtractor): """ diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 35ef4c303..1b2dbf276 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -11,7 +11,6 @@ import time import traceback from .common import InfoExtractor, SearchInfoExtractor -from .subtitles import SubtitlesInfoExtractor from ..jsinterp import JSInterpreter from ..swfinterp import SWFInterpreter from ..compat import ( @@ -185,7 +184,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): return -class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): +class YoutubeIE(YoutubeBaseInfoExtractor): IE_DESC = 'YouTube.com' _VALID_URL = r"""(?x)^ ( @@ -644,7 +643,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): raise ExtractorError( 'Signature extraction failed: ' + tb, cause=e) - def _get_available_subtitles(self, video_id, webpage): + def _get_subtitles(self, video_id, webpage): try: subs_doc = self._download_xml( 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, @@ -658,23 +657,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): lang = track.attrib['lang_code'] if lang in sub_lang_list: continue - params = compat_urllib_parse.urlencode({ - 'lang': lang, - 'v': video_id, - 'fmt': self._downloader.params.get('subtitlesformat', 'srt'), - 'name': track.attrib['name'].encode('utf-8'), - }) - url = 'https://www.youtube.com/api/timedtext?' + params - sub_lang_list[lang] = url + sub_formats = [] + for ext in ['sbv', 'vtt', 'srt']: + params = compat_urllib_parse.urlencode({ + 'lang': lang, + 'v': video_id, + 'fmt': ext, + 'name': track.attrib['name'].encode('utf-8'), + }) + sub_formats.append({ + 'url': 'https://www.youtube.com/api/timedtext?' + params, + 'ext': ext, + }) + sub_lang_list[lang] = sub_formats if not sub_lang_list: self._downloader.report_warning('video doesn\'t have subtitles') return {} return sub_lang_list - def _get_available_automatic_caption(self, video_id, webpage): + def _get_automatic_captions(self, video_id, webpage): """We need the webpage for getting the captions url, pass it as an argument to speed up the process.""" - sub_format = self._downloader.params.get('subtitlesformat', 'srt') self.to_screen('%s: Looking for automatic captions' % video_id) mobj = re.search(r';ytplayer.config = ({.*?});', webpage) err_msg = 'Couldn\'t find automatic captions for %s' % video_id @@ -704,14 +707,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): sub_lang_list = {} for lang_node in caption_list.findall('target'): sub_lang = lang_node.attrib['lang_code'] - params = compat_urllib_parse.urlencode({ - 'lang': original_lang, - 'tlang': sub_lang, - 'fmt': sub_format, - 'ts': timestamp, - 'kind': caption_kind, - }) - sub_lang_list[sub_lang] = caption_url + '&' + params + sub_formats = [] + for ext in ['sbv', 'vtt', 'srt']: + params = compat_urllib_parse.urlencode({ + 'lang': original_lang, + 'tlang': sub_lang, + 'fmt': ext, + 'ts': timestamp, + 'kind': caption_kind, + }) + sub_formats.append({ + 'url': caption_url + '&' + params, + 'ext': ext, + }) + sub_lang_list[sub_lang] = sub_formats return sub_lang_list # An extractor error can be raise by the download process if there are # no automatic captions but there are subtitles @@ -966,10 +975,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # subtitles video_subtitles = self.extract_subtitles(video_id, video_webpage) - - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, video_webpage) - return + automatic_captions = self.extract_automatic_captions(video_id, video_webpage) if 'length_seconds' not in video_info: self._downloader.report_warning('unable to extract video duration') @@ -1118,6 +1124,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'description': video_description, 'categories': video_categories, 'subtitles': video_subtitles, + 'automatic_captions': automatic_captions, 'duration': video_duration, 'age_limit': 18 if age_gate else 0, 'annotations': video_annotations,