X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcommon.py;h=aaca25a12a872eabfe3f43734e0599e7e3d4d78e;hb=15bf934de589f0598b763f8351869c5de69ecad3;hp=359bdd299a508181e23688f87dfb6b8f11b8164d;hpb=c349456ef60d2f638be808bb023635c63df4107c;p=youtube-dl diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 359bdd299..aaca25a12 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -15,13 +15,14 @@ import math from ..compat import ( compat_cookiejar, compat_cookies, + compat_etree_fromstring, compat_getpass, compat_http_client, + compat_os_name, + compat_str, compat_urllib_error, compat_urllib_parse, compat_urlparse, - compat_str, - compat_etree_fromstring, ) from ..utils import ( NO_DEFAULT, @@ -46,6 +47,8 @@ from ..utils import ( xpath_with_ns, determine_protocol, parse_duration, + mimetype2ext, + update_url_query, ) @@ -103,7 +106,7 @@ class InfoExtractor(object): * protocol The protocol that will be used for the actual download, lower-case. "http", "https", "rtsp", "rtmp", "rtmpe", - "m3u8", or "m3u8_native". + "m3u8", "m3u8_native" or "http_dash_segments". * preference Order number of this format. If this field is present and not None, the formats get sorted by this field, regardless of all other values. @@ -156,12 +159,14 @@ class InfoExtractor(object): thumbnail: Full URL to a video thumbnail image. description: Full video description. uploader: Full name of the video uploader. + license: License name the video is licensed under. creator: The main artist who created the video. release_date: The date (YYYYMMDD) when the video was released. timestamp: UNIX timestamp of the moment the video became available. upload_date: Video upload date (YYYYMMDD). If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. + uploader_url: Full URL to a personal webpage of the video uploader. location: Physical location where the video was filmed. subtitles: The available subtitles as a dictionary in the format {language: subformats}. "subformats" is a list sorted from @@ -341,7 +346,7 @@ class InfoExtractor(object): def IE_NAME(self): return compat_str(type(self).__name__[:-2]) - def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers=None, query=None): """ Returns the response handle """ if note is None: self.report_download_webpage(video_id) @@ -350,6 +355,12 @@ class InfoExtractor(object): self.to_screen('%s' % (note,)) else: self.to_screen('%s: %s' % (video_id, note)) + # data, headers and query params will be ignored for `Request` objects + if isinstance(url_or_request, compat_str): + if query: + url_or_request = update_url_query(url_or_request, query) + if data or headers: + url_or_request = sanitized_Request(url_or_request, data, headers or {}) try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -365,13 +376,13 @@ class InfoExtractor(object): self._downloader.report_warning(errmsg) return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers=None, query=None): """ Returns a tuple (page content as string, URL handle) """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query) if urlh is False: assert not fatal return False @@ -424,7 +435,7 @@ class InfoExtractor(object): self.to_screen('Saving request to ' + filename) # Working around MAX_PATH limitation on Windows (see # http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx) - if os.name == 'nt': + if compat_os_name == 'nt': absfilepath = os.path.abspath(filename) if len(absfilepath) > 259: filename = '\\\\?\\' + absfilepath @@ -458,13 +469,13 @@ class InfoExtractor(object): return content - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers=None, query=None): """ Returns the data of the page as a string """ success = False try_count = 0 while success is False: try: - res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding) + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query) success = True except compat_http_client.IncompleteRead as e: try_count += 1 @@ -479,10 +490,10 @@ class InfoExtractor(object): def _download_xml(self, url_or_request, video_id, note='Downloading XML', errnote='Unable to download XML', - transform_source=None, fatal=True, encoding=None): + transform_source=None, fatal=True, encoding=None, data=None, headers=None, query=None): """Return the xml as an xml.etree.ElementTree.Element""" xml_string = self._download_webpage( - url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding) + url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding, data=data, headers=headers, query=query) if xml_string is False: return xml_string if transform_source: @@ -493,10 +504,10 @@ class InfoExtractor(object): note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True, encoding=None): + fatal=True, encoding=None, data=None, headers=None, query=None): json_string = self._download_webpage( url_or_request, video_id, note, errnote, fatal=fatal, - encoding=encoding) + encoding=encoding, data=data, headers=headers, query=query) if (not fatal) and json_string is False: return None return self._parse_json( @@ -593,7 +604,7 @@ class InfoExtractor(object): if mobj: break - if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty(): + if not self._downloader.params.get('no_color') and compat_os_name != 'nt' and sys.stderr.isatty(): _name = '\033[0;34m%s\033[0m' % name else: _name = name @@ -636,7 +647,7 @@ class InfoExtractor(object): downloader_params = self._downloader.params # Attempt to use provided username and password or .netrc data - if downloader_params.get('username', None) is not None: + if downloader_params.get('username') is not None: username = downloader_params['username'] password = downloader_params['password'] elif downloader_params.get('usenetrc', False): @@ -663,7 +674,7 @@ class InfoExtractor(object): return None downloader_params = self._downloader.params - if downloader_params.get('twofactor', None) is not None: + if downloader_params.get('twofactor') is not None: return downloader_params['twofactor'] return compat_getpass('Type %s and press [Return]: ' % note) @@ -744,7 +755,7 @@ class InfoExtractor(object): 'mature': 17, 'restricted': 19, } - return RATING_TABLE.get(rating.lower(), None) + return RATING_TABLE.get(rating.lower()) def _family_friendly_search(self, html): # See http://schema.org/VideoObject @@ -759,7 +770,7 @@ class InfoExtractor(object): '0': 18, 'false': 18, } - return RATING_TABLE.get(family_friendly.lower(), None) + return RATING_TABLE.get(family_friendly.lower()) def _twitter_search_player(self, html): return self._html_search_meta('twitter:player', html, @@ -899,6 +910,16 @@ class InfoExtractor(object): item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'), formats) + @staticmethod + def _remove_duplicate_formats(formats): + format_urls = set() + unique_formats = [] + for f in formats: + if f['url'] not in format_urls: + format_urls.add(f['url']) + unique_formats.append(f) + formats[:] = unique_formats + def _is_valid_url(self, url, video_id, item='video'): url = self._proto_relative_url(url, scheme='http:') # For now assume non HTTP(S) URLs always valid @@ -1022,11 +1043,21 @@ class InfoExtractor(object): return [] m3u8_doc, urlh = res m3u8_url = urlh.geturl() - # A Media Playlist Tag MUST NOT appear in a Master Playlist - # https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3 - # The EXT-X-TARGETDURATION tag is REQUIRED for every M3U8 Media Playlists - # https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1 - if '#EXT-X-TARGETDURATION' in m3u8_doc: + + # We should try extracting formats only from master playlists [1], i.e. + # playlists that describe available qualities. On the other hand media + # playlists [2] should be returned as is since they contain just the media + # without qualities renditions. + # Fortunately, master playlist can be easily distinguished from media + # playlist based on particular tags availability. As of [1, 2] master + # playlist tags MUST NOT appear in a media playist and vice versa. + # As of [3] #EXT-X-TARGETDURATION tag is REQUIRED for every media playlist + # and MUST NOT appear in master playlist thus we can clearly detect media + # playlist with this criterion. + # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.4 + # 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3 + # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1 + if '#EXT-X-TARGETDURATION' in m3u8_doc: # media playlist, return as is return [{ 'url': m3u8_url, 'format_id': m3u8_id, @@ -1073,19 +1104,29 @@ class InfoExtractor(object): 'protocol': entry_protocol, 'preference': preference, } - codecs = last_info.get('CODECS') - if codecs: - # TODO: looks like video codec is not always necessarily goes first - va_codecs = codecs.split(',') - if va_codecs[0]: - f['vcodec'] = va_codecs[0] - if len(va_codecs) > 1 and va_codecs[1]: - f['acodec'] = va_codecs[1] resolution = last_info.get('RESOLUTION') if resolution: width_str, height_str = resolution.split('x') f['width'] = int(width_str) f['height'] = int(height_str) + codecs = last_info.get('CODECS') + if codecs: + vcodec, acodec = [None] * 2 + va_codecs = codecs.split(',') + if len(va_codecs) == 1: + # Audio only entries usually come with single codec and + # no resolution. For more robustness we also check it to + # be mp4 audio. + if not resolution and va_codecs[0].startswith('mp4a'): + vcodec, acodec = 'none', va_codecs[0] + else: + vcodec = va_codecs[0] + else: + vcodec, acodec = va_codecs[:2] + f.update({ + 'acodec': acodec, + 'vcodec': vcodec, + }) if last_media is not None: f['m3u8_media'] = last_media last_media = None @@ -1277,16 +1318,7 @@ class InfoExtractor(object): if not src or src in urls: continue urls.append(src) - ext = textstream.get('ext') or determine_ext(src) - if not ext: - type_ = textstream.get('type') - SUBTITLES_TYPES = { - 'text/vtt': 'vtt', - 'text/srt': 'srt', - 'application/smptett+xml': 'tt', - } - if type_ in SUBTITLES_TYPES: - ext = SUBTITLES_TYPES[type_] + ext = textstream.get('ext') or determine_ext(src) or mimetype2ext(textstream.get('type')) lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang subtitles.setdefault(lang, []).append({ 'url': src, @@ -1422,8 +1454,9 @@ class InfoExtractor(object): continue representation_attrib = adaptation_set.attrib.copy() representation_attrib.update(representation.attrib) - mime_type = representation_attrib.get('mimeType') - content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType') + # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory + mime_type = representation_attrib['mimeType'] + content_type = mime_type.split('/')[0] if content_type == 'text': # TODO implement WebVTT downloading pass @@ -1435,7 +1468,9 @@ class InfoExtractor(object): base_url = base_url_e.text + base_url if re.match(r'^https?://', base_url): break - if not re.match(r'^https?://', base_url): + if mpd_base_url and not re.match(r'^https?://', base_url): + if not mpd_base_url.endswith('/') and not base_url.startswith('/'): + mpd_base_url += '/' base_url = mpd_base_url + base_url representation_id = representation_attrib.get('id') lang = representation_attrib.get('lang') @@ -1444,6 +1479,7 @@ class InfoExtractor(object): f = { 'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id, 'url': base_url, + 'ext': mimetype2ext(mime_type), 'width': int_or_none(representation_attrib.get('width')), 'height': int_or_none(representation_attrib.get('height')), 'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000), @@ -1495,7 +1531,7 @@ class InfoExtractor(object): def _live_title(self, name): """ Generate the title for a live video """ now = datetime.datetime.now() - now_str = now.strftime("%Y-%m-%d %H:%M") + now_str = now.strftime('%Y-%m-%d %H:%M') return name + ' ' + now_str def _int(self, v, name, fatal=False, **kwargs): @@ -1568,7 +1604,7 @@ class InfoExtractor(object): return {} def _get_subtitles(self, *args, **kwargs): - raise NotImplementedError("This method must be implemented by subclasses") + raise NotImplementedError('This method must be implemented by subclasses') @staticmethod def _merge_subtitle_items(subtitle_list1, subtitle_list2): @@ -1594,7 +1630,16 @@ class InfoExtractor(object): return {} def _get_automatic_captions(self, *args, **kwargs): - raise NotImplementedError("This method must be implemented by subclasses") + raise NotImplementedError('This method must be implemented by subclasses') + + def mark_watched(self, *args, **kwargs): + if (self._downloader.params.get('mark_watched', False) and + (self._get_login_info()[0] is not None or + self._downloader.params.get('cookiefile') is not None)): + self._mark_watched(*args, **kwargs) + + def _mark_watched(self, *args, **kwargs): + raise NotImplementedError('This method must be implemented by subclasses') class SearchInfoExtractor(InfoExtractor): @@ -1634,7 +1679,7 @@ class SearchInfoExtractor(InfoExtractor): def _get_n_results(self, query, n): """Get a specified number of results for a query""" - raise NotImplementedError("This method must be implemented by subclasses") + raise NotImplementedError('This method must be implemented by subclasses') @property def SEARCH_KEY(self):