X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=b99a6c505239aeac965e8727c8c106b39eeeaadb;hb=fb778e66dfbcd5ffaf9cb9a7abfda4399c4b684a;hp=9cfff153b12fce1c4db4c1420b6f0caab323a8c2;hpb=95eb771dcda47f948b050da85c7ff22539e3ee12;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py old mode 100644 new mode 100755 index 9cfff153b..b99a6c505 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -3,7 +3,9 @@ from __future__ import absolute_import +import base64 import datetime +import itertools import netrc import os import re @@ -23,7 +25,7 @@ class InfoExtractor(object): Information extractors are the classes that, given a URL, extract information about the video (or videos) the URL refers to. This information includes the real video URL, the video title, author and - others. The information is stored in a dictionary which is then + others. The information is stored in a dictionary which is then passed to the FileDownloader. The FileDownloader processes this information possibly downloading the video to the file system, among other possible outcomes. @@ -32,8 +34,6 @@ class InfoExtractor(object): id: Video identifier. url: Final video URL. - uploader: Nickname of the video uploader, unescaped. - upload_date: Video upload date (YYYYMMDD). title: Video title, unescaped. ext: Video filename extension. @@ -42,6 +42,10 @@ class InfoExtractor(object): format: The video format, defaults to ext (used for --get-format) thumbnail: Full URL to a video thumbnail image. description: One-line video description. + uploader: Full name of the video uploader. + upload_date: Video upload date (YYYYMMDD). + 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 .srt file contents. urlhandle: [internal] The urlHandle to be used to download the file, @@ -100,6 +104,28 @@ class InfoExtractor(object): """Real extraction process. Redefine in subclasses.""" pass + @property + def IE_NAME(self): + return type(self).__name__[:-2] + + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None): + """ Returns the response handle """ + if note is None: + note = u'Downloading video webpage' + self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note)) + try: + return compat_urllib_request.urlopen(url_or_request) + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + if errnote is None: + errnote = u'Unable to download webpage' + raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2]) + + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): + """ Returns the data of the page as a string """ + urlh = self._request_webpage(url_or_request, video_id, note, errnote) + webpage_bytes = urlh.read() + return webpage_bytes.decode('utf-8', 'replace') + class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" @@ -116,7 +142,7 @@ class YoutubeIE(InfoExtractor): |(?: # or the v= param in all its forms (?:watch(?:_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) + (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) v= ) )? # optional -> youtube.com/xxxx is OK @@ -159,7 +185,7 @@ class YoutubeIE(InfoExtractor): '44': '480x854', '45': '720x1280', '46': '1080x1920', - } + } IE_NAME = u'youtube' def suitable(self, url): @@ -219,6 +245,39 @@ class YoutubeIE(InfoExtractor): srt += caption + '\n\n' return srt + def _extract_subtitles(self, video_id): + self.report_video_subtitles_download(video_id) + request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) + try: + srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) + srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) + srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) + if not srt_lang_list: + return (u'WARNING: video has no closed captions', None) + if self._downloader.params.get('subtitleslang', False): + srt_lang = self._downloader.params.get('subtitleslang') + elif 'en' in srt_lang_list: + srt_lang = 'en' + else: + srt_lang = list(srt_lang_list.keys())[0] + if not srt_lang in srt_lang_list: + return (u'WARNING: no closed captions found in the specified language', None) + params = compat_urllib_parse.urlencode({ + 'lang': srt_lang, + 'name': srt_lang_list[srt_lang].encode('utf-8'), + 'v': video_id, + }) + url = 'http://www.youtube.com/api/timedtext?' + params + try: + srt_xml = compat_urllib_request.urlopen(url).read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) + if not srt_xml: + return (u'WARNING: Did not fetch video subtitles', None) + return (None, self._closed_captions_xml_to_srt(srt_xml)) + def _print_formats(self, formats): print('Available formats:') for x in formats: @@ -272,7 +331,7 @@ class YoutubeIE(InfoExtractor): request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) try: self.report_login() - login_results = compat_urllib_request.urlopen(request).read() + login_results = compat_urllib_request.urlopen(request).read().decode('utf-8') if re.search(r'(?i)