diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/common.py | 3 | ||||
| -rw-r--r-- | youtube_dl/extractor/dailymotion.py | 46 | ||||
| -rw-r--r-- | youtube_dl/extractor/subtitles.py | 75 | ||||
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 196 |
4 files changed, 179 insertions, 141 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 8009c2d85..52c4483c9 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -47,7 +47,8 @@ class InfoExtractor(object): uploader_id: Nickname or id of the video uploader. location: Physical location of the video. player_url: SWF Player URL (used for rtmpdump). - subtitles: The subtitle file contents. + subtitles: The subtitle file contents as a dictionary in the format + {language: subtitles}. view_count: How many users have watched the video on the platform. urlhandle: [internal] The urlHandle to be used to download the file, like returned by urllib.request.urlopen diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index fa8c630d0..f54ecc569 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,17 +1,39 @@ import re import json -import itertools +import socket from .common import InfoExtractor +from .subtitles import NoAutoSubtitlesIE + from ..utils import ( + compat_http_client, + compat_urllib_error, compat_urllib_request, + compat_str, get_element_by_attribute, get_element_by_id, ExtractorError, ) -class DailymotionIE(InfoExtractor): + +class DailyMotionSubtitlesIE(NoAutoSubtitlesIE): + + def _get_available_subtitles(self, video_id): + request = compat_urllib_request.Request('https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % 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 {} + info = json.loads(sub_list) + if (info['total'] > 0): + sub_lang_list = dict((l['language'], l['url']) for l in info['list']) + return sub_lang_list + self._downloader.report_warning(u'video doesn\'t have subtitles') + return {} + +class DailymotionIE(DailyMotionSubtitlesIE): """Information Extractor for Dailymotion""" _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' @@ -21,7 +43,7 @@ class DailymotionIE(InfoExtractor): u'file': u'x33vw9.mp4', u'md5': u'392c4b85a60a90dc4792da41ce3144eb', u'info_dict': { - u"uploader": u"Alex and Van .", + u"uploader": u"Alex and Van .", u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\"" } } @@ -63,14 +85,27 @@ class DailymotionIE(InfoExtractor): for key in ['stream_h264_hd1080_url','stream_h264_hd_url', 'stream_h264_hq_url','stream_h264_url', 'stream_h264_ld_url']: - if info.get(key):#key in info and info[key]: + if info.get(key): # key in info and info[key]: max_quality = key - self.to_screen(u'Using %s' % key) + self.to_screen(u'%s: Using %s' % (video_id, key)) break else: raise ExtractorError(u'Unable to extract video URL') video_url = info[max_quality] + # subtitles + video_subtitles = None + video_webpage = None + + if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False): + video_subtitles = self._extract_subtitles(video_id) + elif self._downloader.params.get('writeautomaticsub', False): + video_subtitles = self._request_automatic_caption(video_id, video_webpage) + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id) + return + return [{ 'id': video_id, 'url': video_url, @@ -78,6 +113,7 @@ class DailymotionIE(InfoExtractor): 'upload_date': video_upload_date, 'title': self._og_search_title(webpage), 'ext': video_extension, + 'subtitles': video_subtitles, 'thumbnail': info['thumbnail_url'] }] diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py new file mode 100644 index 000000000..caacea5fe --- /dev/null +++ b/youtube_dl/extractor/subtitles.py @@ -0,0 +1,75 @@ +import socket + +from .common import InfoExtractor + +from ..utils import ( + compat_http_client, + compat_urllib_error, + compat_urllib_request, + compat_str, +) + + +class SubtitlesIE(InfoExtractor): + + def _list_available_subtitles(self, video_id): + """ outputs the available subtitles for the video """ + sub_lang_list = self._get_available_subtitles(video_id) + sub_lang = ",".join(list(sub_lang_list.keys())) + self.to_screen(u'%s: Available subtitles for video: %s' % + (video_id, sub_lang)) + + def _extract_subtitles(self, video_id): + """ returns {sub_lang: sub} or {} if subtitles not found """ + sub_lang_list = self._get_available_subtitles(video_id) + 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') + 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, 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_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))) + return + if not sub: + self._downloader.report_warning(u'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 + + +class NoAutoSubtitlesIE(SubtitlesIE): + """ A subtitle class for the servers that don't support auto-captions""" + + def _request_automatic_caption(self, video_id, webpage): + self._downloader.report_warning(u'Automatic Captions not supported by this server') + return {} diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index c539b6891..f6ffb86c3 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, @@ -23,114 +24,67 @@ from ..utils import ( orderedSet, ) -class YoutubeBaseInfoExtractor(InfoExtractor): - """Provide base functions for Youtube extractors""" - _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' - _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' - _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' - _NETRC_MACHINE = 'youtube' - # If True it will raise an error if no login info is provided - _LOGIN_REQUIRED = False - - def report_lang(self): - """Report attempt to set language.""" - self.to_screen(u'Setting language') - - def _set_language(self): - request = compat_urllib_request.Request(self._LANG_URL) - try: - self.report_lang() - compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning(u'unable to set language: %s' % compat_str(err)) - return False - return True - - def _login(self): - (username, password) = self._get_login_info() - # No authentication to be performed - if username is None: - if self._LOGIN_REQUIRED: - raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True) - return False - - request = compat_urllib_request.Request(self._LOGIN_URL) - try: - login_page = 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 fetch login page: %s' % compat_str(err)) - return False - - galx = None - dsh = None - match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page) - if match: - galx = match.group(1) - match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page) - if match: - dsh = match.group(1) - - # Log in - login_form_strs = { - u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', - u'Email': username, - u'GALX': galx, - u'Passwd': password, - u'PersistentCookie': u'yes', - u'_utf8': u'霱', - u'bgresponse': u'js_disabled', - u'checkConnection': u'', - u'checkedDomains': u'youtube', - u'dnConn': u'', - u'dsh': dsh, - u'pstMsg': u'0', - u'rmShown': u'1', - u'secTok': u'', - u'signIn': u'Sign in', - u'timeStmp': u'', - u'service': u'youtube', - u'uilel': u'3', - u'hl': u'en_US', - } - # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode - # chokes on unicode - login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) - login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') - request = compat_urllib_request.Request(self._LOGIN_URL, login_data) + +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: - self.report_login() - login_results = compat_urllib_request.urlopen(request).read().decode('utf-8') - if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: - self._downloader.report_warning(u'unable to log in: bad username or password') - return False + 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 log in: %s' % compat_str(err)) - return False - return True - - def _confirm_age(self): - age_form = { - 'next_url': '/', - 'action_confirm': 'Confirm', - } - request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) + 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: - self.report_age_confirmation() - compat_urllib_request.urlopen(request).read().decode('utf-8') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) - return True + 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 _real_initialize(self): - if self._downloader is None: - return - if not self._set_language(): - return - if not self._login(): - return - self._confirm_age() -class YoutubeIE(YoutubeBaseInfoExtractor): +class YoutubeIE(YoutubeSubtitlesIE): IE_DESC = u'YouTube.com' _VALID_URL = r"""^ ( @@ -141,7 +95,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?: # the various things that can precede the ID: (?:(?:v|embed|e)/) # v/ or embed/ or e/ |(?: # or the v= param in all its forms - (?:(?:watch|movie)(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) + (?:watch|movie(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) (?:\?|\#!?) # the params delimiter ? or # or #! (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) v= @@ -384,19 +338,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): """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) @@ -736,25 +677,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # subtitles video_subtitles = None - if self._downloader.params.get('writesubtitles', False): - video_subtitles = self._extract_subtitle(video_id) - if video_subtitles: - (sub_error, sub_lang, sub) = video_subtitles[0] - if sub_error: - self._downloader.report_warning(sub_error) - - if self._downloader.params.get('writeautomaticsub', False): + if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False): + video_subtitles = self._extract_subtitles(video_id) + elif self._downloader.params.get('writeautomaticsub', False): video_subtitles = self._request_automatic_caption(video_id, video_webpage) - (sub_error, sub_lang, sub) = video_subtitles[0] - if sub_error: - self._downloader.report_warning(sub_error) - - if self._downloader.params.get('allsubtitles', False): - video_subtitles = self._extract_all_subtitles(video_id) - for video_subtitle in video_subtitles: - (sub_error, sub_lang, sub) = video_subtitle - if sub_error: - self._downloader.report_warning(sub_error) if self._downloader.params.get('listsubtitles', False): self._list_available_subtitles(video_id) |