From 1f343eaabbb9e0daf67363b7737833cf5e2a3e16 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Isma=C3=ABl=20Mej=C3=ADa?= Date: Sat, 2 Nov 2013 18:01:05 +0100 Subject: [PATCH 1/3] [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. --- youtube_dl/extractor/dailymotion.py | 6 +++--- youtube_dl/extractor/subtitles.py | 12 ++++++------ youtube_dl/extractor/youtube.py | 2 +- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 7d8353946..3aef82bcf 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -113,9 +113,9 @@ def _real_extract(self, url): video_url = info[max_quality] # subtitles - video_subtitles = self.extract_subtitles(video_id) + video_subtitles = self.extract_subtitles(video_id, webpage) if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id) + self._list_available_subtitles(video_id, webpage) return return [{ @@ -129,7 +129,7 @@ def _real_extract(self, url): 'thumbnail': info['thumbnail_url'] }] - def _get_available_subtitles(self, video_id): + def _get_available_subtitles(self, video_id, webpage): try: sub_list = self._download_webpage( 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py index 90de7de3a..4b4c5235d 100644 --- a/youtube_dl/extractor/subtitles.py +++ b/youtube_dl/extractor/subtitles.py @@ -12,9 +12,9 @@ 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, webpage=None): + 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' % @@ -23,7 +23,7 @@ def _list_available_subtitles(self, video_id, webpage=None): self.to_screen(u'%s: Available automatic captions for video: %s' % (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 subtitles aren't requested. @@ -32,9 +32,9 @@ def extract_subtitles(self, video_id, video_webpage=None): return None available_subs_list = {} 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): - 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 return {} @@ -74,7 +74,7 @@ def _request_subtitle_url(self, sub_lang, url): return 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 Must be redefined by the subclasses diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 4347651d7..d7c9b38f9 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1099,7 +1099,7 @@ def _static_decrypt_signature(self, s, video_id, player_url, age_gate): 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): + def _get_available_subtitles(self, video_id, webpage): try: sub_list = self._download_webpage( 'http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, From a9a3876d55be943a7eaf505cbeb8fb862514db6c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Isma=C3=ABl=20Mej=C3=ADa?= Date: Sat, 2 Nov 2013 19:48:39 +0100 Subject: [PATCH 2/3] [ted] Added support for subtitle download --- test/test_ted_subtitles.py | 63 +++++++++++++++++++++++++++++++++++++ youtube_dl/extractor/ted.py | 28 ++++++++++++++--- 2 files changed, 87 insertions(+), 4 deletions(-) create mode 100644 test/test_ted_subtitles.py diff --git a/test/test_ted_subtitles.py b/test/test_ted_subtitles.py new file mode 100644 index 000000000..3283253ab --- /dev/null +++ b/test/test_ted_subtitles.py @@ -0,0 +1,63 @@ +#!/usr/bin/env python + +import sys +import unittest +import hashlib + +# Allow direct execution +import os +sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from youtube_dl.extractor import TEDIE +from youtube_dl.utils import * +from helper import FakeYDL + +md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() + +class TestTedSubtitles(unittest.TestCase): + def setUp(self): + self.DL = FakeYDL() + self.url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html' + def getInfoDict(self): + IE = TEDIE(self.DL) + info_dict = IE.extract(self.url) + return info_dict + def getSubtitles(self): + info_dict = self.getInfoDict() + return info_dict[0]['subtitles'] + def test_no_writesubtitles(self): + subtitles = self.getSubtitles() + self.assertEqual(subtitles, None) + def test_subtitles(self): + self.DL.params['writesubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(md5(subtitles['en']), '2154f31ff9b9f89a0aa671537559c21d') + def test_subtitles_lang(self): + self.DL.params['writesubtitles'] = True + self.DL.params['subtitleslangs'] = ['fr'] + subtitles = self.getSubtitles() + self.assertEqual(md5(subtitles['fr']), '7616cbc6df20ec2c1204083c83871cf6') + def test_allsubtitles(self): + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(len(subtitles.keys()), 28) + def test_list_subtitles(self): + self.DL.params['listsubtitles'] = True + info_dict = self.getInfoDict() + self.assertEqual(info_dict, [None]) + def test_automatic_captions(self): + self.DL.params['writeautomaticsub'] = True + self.DL.params['subtitleslang'] = ['en'] + subtitles = self.getSubtitles() + self.assertTrue(len(subtitles.keys()) == 0) + def test_multiple_langs(self): + self.DL.params['writesubtitles'] = True + langs = ['es', 'fr', 'de'] + self.DL.params['subtitleslangs'] = langs + subtitles = self.getSubtitles() + for lang in langs: + self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang) + +if __name__ == '__main__': + unittest.main() diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index dfa1176a3..239e2a448 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -1,10 +1,9 @@ import json import re -from .common import InfoExtractor +from .subtitles import SubtitlesInfoExtractor - -class TEDIE(InfoExtractor): +class TEDIE(SubtitlesInfoExtractor): _VALID_URL=r'''http://www\.ted\.com/ ( ((?Pplaylists)/(?P\d+)) # We have a playlist @@ -82,11 +81,21 @@ def _talk_info(self, url, video_id=0): 'url': stream['file'], 'format': stream['id'] } for stream in info['htmlStreams']] + + video_id = info['id'] + + # subtitles + video_subtitles = self.extract_subtitles(video_id, webpage) + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, webpage) + return + info = { - 'id': info['id'], + 'id': video_id, 'title': title, 'thumbnail': thumbnail, 'description': desc, + 'subtitles': video_subtitles, 'formats': formats, } @@ -94,3 +103,14 @@ def _talk_info(self, url, video_id=0): info.update(info['formats'][-1]) return info + + def _get_available_subtitles(self, video_id, webpage): + options = self._search_regex(r'(?:)', webpage, 'subtitles_language_select', flags=re.DOTALL) + languages = re.findall(r'(?: