X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcommon.py;h=7757bf9502169b79e498a7f26ba0b227b44efe91;hb=08f2a92c9c23cf460b00a290b5b3819c7972231b;hp=31599bf52a8e01046b109c05c4d09dc142b1dc8c;hpb=4cd95bcbc34d74e506e6158251d50d83697da5fe;p=youtube-dl diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 31599bf52..7757bf950 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -23,11 +23,11 @@ from ..compat import ( ) from ..utils import ( age_restricted, + bug_reports_message, clean_html, compiled_regex_type, ExtractorError, float_or_none, - HEADRequest, int_or_none, RegexNotFoundError, sanitize_filename, @@ -151,8 +151,14 @@ class InfoExtractor(object): If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. location: Physical location where the video was filmed. - subtitles: The subtitle file contents as a dictionary in the format - {language: subtitles}. + subtitles: The available subtitles as a dictionary in the format + {language: subformats}. "subformats" is a list sorted from + lower to higher preference, each element is a dictionary + 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 @@ -319,7 +325,7 @@ 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): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None): """ Returns a tuple (page content as string, URL handle) """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): @@ -329,14 +335,11 @@ class InfoExtractor(object): if urlh is False: assert not fatal return False - content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal) + content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal, encoding=encoding) return (content, urlh) - def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None): - content_type = urlh.headers.get('Content-Type', '') - webpage_bytes = urlh.read() - if prefix is not None: - webpage_bytes = prefix + webpage_bytes + @staticmethod + def _guess_encoding_from_content(content_type, webpage_bytes): m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) if m: encoding = m.group(1) @@ -349,6 +352,16 @@ class InfoExtractor(object): encoding = 'utf-16' else: encoding = 'utf-8' + + return encoding + + def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None): + content_type = urlh.headers.get('Content-Type', '') + webpage_bytes = urlh.read() + if prefix is not None: + webpage_bytes = prefix + webpage_bytes + if not encoding: + encoding = self._guess_encoding_from_content(content_type, webpage_bytes) if self._downloader.params.get('dump_intermediate_pages', False): try: url = url_or_request.get_full_url() @@ -392,16 +405,26 @@ class InfoExtractor(object): if blocked_iframe: msg += ' Visit %s for more details' % blocked_iframe raise ExtractorError(msg, expected=True) + if '
(.*?)
', + content, 'block message', default=None) + if block_msg: + msg += ' (Message: "%s")' % block_msg.replace('\n', ' ') + raise ExtractorError(msg, expected=True) return content - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=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) + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding) success = True except compat_http_client.IncompleteRead as e: try_count += 1 @@ -416,10 +439,10 @@ 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): + transform_source=None, fatal=True, encoding=None): """Return the xml as an xml.etree.ElementTree.Element""" xml_string = self._download_webpage( - url_or_request, video_id, note, errnote, fatal=fatal) + url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding) if xml_string is False: return xml_string if transform_source: @@ -430,9 +453,10 @@ class InfoExtractor(object): note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True): + fatal=True, encoding=None): json_string = self._download_webpage( - url_or_request, video_id, note, errnote, fatal=fatal) + url_or_request, video_id, note, errnote, fatal=fatal, + encoding=encoding) if (not fatal) and json_string is False: return None return self._parse_json( @@ -477,7 +501,7 @@ class InfoExtractor(object): # Methods for following #608 @staticmethod - def url_result(url, ie=None, video_id=None): + def url_result(url, ie=None, video_id=None, video_title=None): """Returns a url that points to a page that should be processed""" # TODO: ie should be the class used for getting the info video_info = {'_type': 'url', @@ -485,6 +509,8 @@ class InfoExtractor(object): 'ie_key': ie} if video_id is not None: video_info['id'] = video_id + if video_title is not None: + video_info['title'] = video_title return video_info @staticmethod @@ -531,8 +557,7 @@ class InfoExtractor(object): elif fatal: raise RegexNotFoundError('Unable to extract %s' % _name) else: - self._downloader.report_warning('unable to extract %s; ' - 'please report this issue on http://yt-dl.org/bug' % _name) + self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message()) return None def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None): @@ -752,6 +777,10 @@ class InfoExtractor(object): 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 + if not (url.startswith('http://') or url.startswith('https://')): + return True try: self._request_webpage(url, video_id, 'Checking %s URL' % item) return True @@ -799,11 +828,11 @@ class InfoExtractor(object): media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media') for i, media_el in enumerate(media_nodes): if manifest_version == '2.0': - manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/' - + (media_el.attrib.get('href') or media_el.attrib.get('url'))) + manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/' + + (media_el.attrib.get('href') or media_el.attrib.get('url'))) tbr = int_or_none(media_el.attrib.get('bitrate')) formats.append({ - 'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])), + 'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])), 'url': manifest_url, 'ext': 'flv', 'tbr': tbr, @@ -820,11 +849,11 @@ class InfoExtractor(object): m3u8_id=None): formats = [{ - 'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])), + 'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])), 'url': m3u8_url, 'ext': ext, 'protocol': 'm3u8', - 'preference': -1, + 'preference': preference - 1 if preference else -1, 'resolution': 'multiple', 'format_note': 'Quality selection URL', }] @@ -839,7 +868,7 @@ class InfoExtractor(object): note='Downloading m3u8 information', errnote='Failed to download m3u8 information') last_info = None - last_media= None + last_media = None kv_rex = re.compile( r'(?P