X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9d6a3ba754469c85b7f0f88714203f99ac69087a..291f6705b350d9f813b12efb37b7963555758994:/youtube_dl/extractor/common.py?ds=sidebyside diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index a2548db..e5f8136 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -19,6 +19,7 @@ from ..compat import ( compat_cookies, compat_etree_fromstring, compat_getpass, + compat_integer_types, compat_http_client, compat_os_name, compat_str, @@ -51,6 +52,7 @@ from ..utils import ( GeoUtils, int_or_none, js_to_json, + JSON_LD_RE, mimetype2ext, orderedSet, parse_codecs, @@ -67,6 +69,7 @@ from ..utils import ( update_url_query, urljoin, url_basename, + url_or_none, xpath_element, xpath_text, xpath_with_ns, @@ -209,6 +212,11 @@ class InfoExtractor(object): 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. + channel: Full name of the channel the video is uploaded on. + Note that channel fields may or may not repeat uploader + fields. This depends on a particular extractor. + channel_id: Id of the channel. + channel_url: Full URL to a channel webpage. location: Physical location where the video was filmed. subtitles: The available subtitles as a dictionary in the format {tag: subformats}. "tag" is usually a language code, and @@ -548,8 +556,26 @@ 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, data=None, headers={}, query={}): - """ Returns the response handle """ + @staticmethod + def __can_accept_status_code(err, expected_status): + assert isinstance(err, compat_urllib_error.HTTPError) + if expected_status is None: + return False + if isinstance(expected_status, compat_integer_types): + return err.code == expected_status + elif isinstance(expected_status, (list, tuple)): + return err.code in expected_status + elif callable(expected_status): + return expected_status(err.code) is True + else: + assert False + + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}, expected_status=None): + """ + Return the response handle. + + See _download_webpage docstring for arguments specification. + """ if note is None: self.report_download_webpage(video_id) elif note is not False: @@ -578,6 +604,15 @@ class InfoExtractor(object): try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + if isinstance(err, compat_urllib_error.HTTPError): + if self.__can_accept_status_code(err, expected_status): + # Retain reference to error to prevent file object from + # being closed before it can be read. Works around the + # effects of + # introduced in Python 3.4.1. + err.fp._error = err + return err.fp + if errnote is False: return False if errnote is None: @@ -590,13 +625,17 @@ 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, data=None, headers={}, query={}): - """ Returns a tuple (page content as string, URL handle) """ + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None): + """ + Return a tuple (page content as string, URL handle). + + See _download_webpage docstring for arguments specification. + """ # 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, data=data, headers=headers, query=query) + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query, expected_status=expected_status) if urlh is False: assert not fatal return False @@ -685,13 +724,52 @@ 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, data=None, headers={}, query={}): - """ Returns the data of the page as a string """ + def _download_webpage( + self, url_or_request, video_id, note=None, errnote=None, + fatal=True, tries=1, timeout=5, encoding=None, data=None, + headers={}, query={}, expected_status=None): + """ + Return the data of the page as a string. + + Arguments: + url_or_request -- plain text URL as a string or + a compat_urllib_request.Requestobject + video_id -- Video/playlist/item identifier (string) + + Keyword arguments: + note -- note printed before downloading (string) + errnote -- note printed in case of an error (string) + fatal -- flag denoting whether error should be considered fatal, + i.e. whether it should cause ExtractionError to be raised, + otherwise a warning will be reported and extraction continued + tries -- number of tries + timeout -- sleep interval between tries + encoding -- encoding for a page content decoding, guessed automatically + when not explicitly specified + data -- POST data (bytes) + headers -- HTTP headers (dict) + query -- URL query (dict) + expected_status -- allows to accept failed HTTP requests (non 2xx + status code) by explicitly specifying a set of accepted status + codes. Can be any of the following entities: + - an integer type specifying an exact failed status code to + accept + - a list or a tuple of integer types specifying a list of + failed status codes to accept + - a callable accepting an actual failed status code and + returning True if it should be accepted + Note that this argument does not affect success status codes (2xx) + which are always accepted. + """ + 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, data=data, headers=headers, query=query) + res = self._download_webpage_handle( + url_or_request, video_id, note, errnote, fatal, + encoding=encoding, data=data, headers=headers, query=query, + expected_status=expected_status) success = True except compat_http_client.IncompleteRead as e: try_count += 1 @@ -707,11 +785,17 @@ class InfoExtractor(object): def _download_xml_handle( self, url_or_request, video_id, note='Downloading XML', errnote='Unable to download XML', transform_source=None, - fatal=True, encoding=None, data=None, headers={}, query={}): - """Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle)""" + fatal=True, encoding=None, data=None, headers={}, query={}, + expected_status=None): + """ + Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle). + + See _download_webpage docstring for arguments specification. + """ res = self._download_webpage_handle( url_or_request, video_id, note, errnote, fatal=fatal, - encoding=encoding, data=data, headers=headers, query=query) + encoding=encoding, data=data, headers=headers, query=query, + expected_status=expected_status) if res is False: return res xml_string, urlh = res @@ -719,15 +803,21 @@ class InfoExtractor(object): xml_string, video_id, transform_source=transform_source, fatal=fatal), urlh - def _download_xml(self, url_or_request, video_id, - note='Downloading XML', errnote='Unable to download XML', - transform_source=None, fatal=True, encoding=None, - data=None, headers={}, query={}): - """Return the xml as an xml.etree.ElementTree.Element""" + def _download_xml( + self, url_or_request, video_id, + note='Downloading XML', errnote='Unable to download XML', + transform_source=None, fatal=True, encoding=None, + data=None, headers={}, query={}, expected_status=None): + """ + Return the xml as an xml.etree.ElementTree.Element. + + See _download_webpage docstring for arguments specification. + """ res = self._download_xml_handle( url_or_request, video_id, note=note, errnote=errnote, transform_source=transform_source, fatal=fatal, encoding=encoding, - data=data, headers=headers, query=query) + data=data, headers=headers, query=query, + expected_status=expected_status) return res if res is False else res[0] def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True): @@ -745,11 +835,17 @@ class InfoExtractor(object): def _download_json_handle( self, url_or_request, video_id, note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True, encoding=None, data=None, headers={}, query={}): - """Return a tuple (JSON object, URL handle)""" + fatal=True, encoding=None, data=None, headers={}, query={}, + expected_status=None): + """ + Return a tuple (JSON object, URL handle). + + See _download_webpage docstring for arguments specification. + """ res = self._download_webpage_handle( url_or_request, video_id, note, errnote, fatal=fatal, - encoding=encoding, data=data, headers=headers, query=query) + encoding=encoding, data=data, headers=headers, query=query, + expected_status=expected_status) if res is False: return res json_string, urlh = res @@ -760,11 +856,18 @@ class InfoExtractor(object): def _download_json( self, url_or_request, video_id, note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True, encoding=None, data=None, headers={}, query={}): + fatal=True, encoding=None, data=None, headers={}, query={}, + expected_status=None): + """ + Return the JSON object as a dict. + + See _download_webpage docstring for arguments specification. + """ res = self._download_json_handle( url_or_request, video_id, note=note, errnote=errnote, transform_source=transform_source, fatal=fatal, encoding=encoding, - data=data, headers=headers, query=query) + data=data, headers=headers, query=query, + expected_status=expected_status) return res if res is False else res[0] def _parse_json(self, json_string, video_id, transform_source=None, fatal=True): @@ -1058,8 +1161,7 @@ class InfoExtractor(object): def _search_json_ld(self, html, video_id, expected_type=None, **kwargs): json_ld = self._search_regex( - r'(?s)]+type=(["\'])application/ld\+json\1[^>]*>(?P.+?)', - html, 'JSON-LD', group='json_ld', **kwargs) + JSON_LD_RE, html, 'JSON-LD', group='json_ld', **kwargs) default = kwargs.get('default', NO_DEFAULT) if not json_ld: return default if default is not NO_DEFAULT else {} @@ -1117,10 +1219,10 @@ class InfoExtractor(object): def extract_video_object(e): assert e['@type'] == 'VideoObject' info.update({ - 'url': e.get('contentUrl'), + 'url': url_or_none(e.get('contentUrl')), 'title': unescapeHTML(e.get('name')), 'description': unescapeHTML(e.get('description')), - 'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'), + 'thumbnail': url_or_none(e.get('thumbnailUrl') or e.get('thumbnailURL')), 'duration': parse_duration(e.get('duration')), 'timestamp': unified_timestamp(e.get('uploadDate')), 'filesize': float_or_none(e.get('contentSize')), @@ -1610,9 +1712,9 @@ class InfoExtractor(object): # However, this is not always respected, for example, [2] # contains EXT-X-STREAM-INF tag which references AUDIO # rendition group but does not have CODECS and despite - # referencing audio group an audio group, it represents - # a complete (with audio and video) format. So, for such cases - # we will ignore references to rendition groups and treat them + # referencing an audio group it represents a complete + # (with audio and video) format. So, for such cases we will + # ignore references to rendition groups and treat them # as complete formats. if audio_group_id and codecs and f.get('vcodec') != 'none': audio_group = groups.get(audio_group_id) @@ -1768,9 +1870,7 @@ class InfoExtractor(object): 'height': height, }) formats.extend(m3u8_formats) - continue - - if src_ext == 'f4m': + elif src_ext == 'f4m': f4m_url = src_url if not f4m_params: f4m_params = { @@ -1780,9 +1880,13 @@ class InfoExtractor(object): f4m_url += '&' if '?' in f4m_url else '?' f4m_url += compat_urllib_parse_urlencode(f4m_params) formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False)) - continue - - if src_url.startswith('http') and self._is_valid_url(src, video_id): + elif src_ext == 'mpd': + formats.extend(self._extract_mpd_formats( + src_url, video_id, mpd_id='dash', fatal=False)) + elif re.search(r'\.ism/[Mm]anifest', src_url): + formats.extend(self._extract_ism_formats( + src_url, video_id, ism_id='mss', fatal=False)) + elif src_url.startswith('http') and self._is_valid_url(src, video_id): http_count += 1 formats.append({ 'url': src_url, @@ -1793,7 +1897,6 @@ class InfoExtractor(object): 'width': width, 'height': height, }) - continue return formats @@ -2015,7 +2118,21 @@ class InfoExtractor(object): representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info) def prepare_template(template_name, identifiers): - t = representation_ms_info[template_name] + tmpl = representation_ms_info[template_name] + # First of, % characters outside $...$ templates + # must be escaped by doubling for proper processing + # by % operator string formatting used further (see + # https://github.com/rg3/youtube-dl/issues/16867). + t = '' + in_template = False + for c in tmpl: + t += c + if c == '$': + in_template = not in_template + elif c == '%' and not in_template: + t += c + # Next, $...$ templates are translated to their + # %(...) counterparts to be used with % operator t = t.replace('$RepresentationID$', representation_id) t = re.sub(r'\$(%s)\$' % '|'.join(identifiers), r'%(\1)d', t) t = re.sub(r'\$(%s)%%([^$]+)\$' % '|'.join(identifiers), r'%(\1)\2', t) @@ -2346,6 +2463,8 @@ class InfoExtractor(object): media_info['subtitles'].setdefault(lang, []).append({ 'url': absolute_url(src), }) + for f in media_info['formats']: + f.setdefault('http_headers', {})['Referer'] = base_url if media_info['formats'] or media_info['subtitles']: entries.append(media_info) return entries