X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgdcvault.py;h=de14ae1fb1edd0600488b8f04c7b400bf310ef5a;hb=cc7fec5818254f4679896823c7de9d17f50201ca;hp=a1e4c32212343a8413276bd48143e7ec1c03380b;hpb=9e68f9fdf1efa6b6afe141feb27d9626e40c3056;p=youtube-dl diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py index a1e4c3221..de14ae1fb 100644 --- a/youtube_dl/extractor/gdcvault.py +++ b/youtube_dl/extractor/gdcvault.py @@ -1,61 +1,166 @@ from __future__ import unicode_literals import re -import json -import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import unified_strdate +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, +) class GDCVaultIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P\d+)/(?P(\w|-)+)' + _TESTS = [ + { + 'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple', + 'md5': '7ce8388f544c88b7ac11c7ab1b593704', + 'info_dict': { + 'id': '1019721', + 'ext': 'mp4', + 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)' + } + }, + { + 'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of', + 'info_dict': { + 'id': '1015683', + 'ext': 'flv', + 'title': 'Embracing the Dark Art of Mathematical Modeling in AI' + }, + 'params': { + 'skip_download': True, # Requires rtmpdump + } + }, + { + 'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or', + 'md5': 'a5eb77996ef82118afbbe8e48731b98e', + 'info_dict': { + 'id': '1015301', + 'ext': 'flv', + 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment', + } + } + ] + + def _parse_mp4(self, xml_description): + video_formats = [] + mp4_video = xml_description.find('./metadata/mp4video') + if mp4_video is None: + return None - _TEST = { - u'url': u'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple', - u'md5': u'7ce8388f544c88b7ac11c7ab1b593704', - u'info_dict': { - u"id": u"1019721", - u"ext": u"mp4", - u"title": u"Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)" + mobj = re.match(r'(?Phttps?://.*?/).*', mp4_video.text) + video_root = mobj.group('root') + formats = xml_description.findall('./metadata/MBRVideos/MBRVideo') + for format in formats: + mobj = re.match(r'mp4\:(?P.*)', format.find('streamName').text) + url = video_root + mobj.group('path') + vbr = format.find('bitrate').text + video_formats.append({ + 'url': url, + 'vbr': int(vbr), + }) + return video_formats + + def _parse_flv(self, xml_description): + video_formats = [] + akami_url = xml_description.find('./metadata/akamaiHost').text + slide_video_path = xml_description.find('./metadata/slideVideo').text + video_formats.append({ + 'url': 'rtmp://' + akami_url + '/' + slide_video_path, + 'format_note': 'slide deck video', + 'quality': -2, + 'preference': -2, + 'format_id': 'slides', + }) + speaker_video_path = xml_description.find('./metadata/speakerVideo').text + video_formats.append({ + 'url': 'rtmp://' + akami_url + '/' + speaker_video_path, + 'format_note': 'speaker video', + 'quality': -1, + 'preference': -1, + 'format_id': 'speaker', + }) + return video_formats + + def _login(self, webpage_url, video_id): + (username, password) = self._get_login_info() + if username is None or password is None: + self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.') + return None + + mobj = re.match(r'(?Phttps?://.*?/).*', webpage_url) + login_url = mobj.group('root_url') + 'api/login.php' + logout_url = mobj.group('root_url') + 'logout' + + login_form = { + 'email': username, + 'password': password, } - } + + request = compat_urllib_request.Request(login_url, compat_urllib_parse.urlencode(login_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + self._download_webpage(request, video_id, 'Logging in') + start_page = self._download_webpage(webpage_url, video_id, 'Getting authenticated video page') + self._download_webpage(logout_url, video_id, 'Logging out') + + return start_page def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage_url = 'http://www.gdcvault.com/play/' + video_id - start_page = self._download_webpage(webpage_url, video_id) - self.report_extraction(video_id) + direct_url = self._search_regex( + r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);', + start_page, 'url', default=None) + if direct_url: + video_url = 'http://www.gdcvault.com/' + direct_url + title = self._html_search_regex( + r'Session Name\s*(.*?)', + start_page, 'title') - xml_root = self._html_search_regex(r'', start_page, 'xml filename') - xml_decription_url = xml_root + 'xml/' + xml_name + return { + 'id': video_id, + 'url': video_url, + 'ext': 'flv', + 'title': title, + } - xml_description = self._download_xml(xml_decription_url, video_id) + xml_root = self._html_search_regex( + r'', + start_page, 'xml root') - video_title = xml_description.find('./metadata/title').text + xml_name = self._html_search_regex( + r'', start_page, 'xml filename') - mp4_video = xml_description.find('./metadata/mp4video').text - mobj = re.match(r'(?Phttps?://.*?/).*', mp4_video) - video_root = mobj.group('root') + xml_decription_url = xml_root + 'xml/' + xml_name + xml_description = self._download_xml(xml_decription_url, video_id) - formats = xml_description.findall('./metadata/MBRVideos/MBRVideo') - video_formats = [] - for format in formats: - mobj = re.match(r'mp4\:(?P.*)', format.find('streamName').text) - url = video_root + mobj.group('path') - vbr = format.find('bitrate').text - video_formats.append({ - 'url': url, - 'vbr': int(vbr), - }) + video_title = xml_description.find('./metadata/title').text + video_formats = self._parse_mp4(xml_description) + if video_formats is None: + video_formats = self._parse_flv(xml_description) - return [{ + return { 'id': video_id, - 'formats': video_formats, 'title': video_title, - }] + 'formats': video_formats, + }