X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fescapist.py;h=4cd815ebc4c1aabfc321cf5f3c74f8328be81d1f;hb=adc13b0748784db87faef580929b1adadaff732e;hp=98b6982770d95e1c10b59b5d4e3970a2ba0bf99c;hpb=596ac6e31f6baaadf8280e2c54ca90a7cf2fbc2a;p=youtube-dl diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index 98b698277..4cd815ebc 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -1,82 +1,111 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, -) from ..utils import ( - ExtractorError, - js_to_json, + determine_ext, + clean_html, + int_or_none, + float_or_none, ) +def _decrypt_config(key, string): + a = '' + i = '' + r = '' + + while len(a) < (len(string) / 2): + a += key + + a = a[0:int(len(string) / 2)] + + t = 0 + while t < len(string): + i += chr(int(string[t] + string[t + 1], 16)) + t += 2 + + icko = [s for s in i] + + for t, c in enumerate(a): + r += chr(ord(c) ^ ord(icko[t])) + + return r + + class EscapistIE(InfoExtractor): - _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P[0-9]+)-[^/?#]*(?:$|[?#])' - _TEST = { + _VALID_URL = r'https?://?(?:(?:www|v1)\.)?escapistmagazine\.com/videos/view/[^/]+/(?P[0-9]+)' + _TESTS = [{ 'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate', 'md5': 'ab3a706c681efca53f0a35f1415cf0d1', 'info_dict': { 'id': '6618', 'ext': 'mp4', 'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", - 'uploader_id': 'the-escapist-presents', - 'uploader': 'The Escapist Presents', 'title': "Breaking Down Baldur's Gate", + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 264, + 'uploader': 'The Escapist', + } + }, { + 'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer', + 'md5': '9e8c437b0dbb0387d3bd3255ca77f6bf', + 'info_dict': { + 'id': '10044', + 'ext': 'mp4', + 'description': 'This week, Zero Punctuation reviews Evolve.', + 'title': 'Evolve - One vs Multiplayer', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 304, + 'uploader': 'The Escapist', } - } + }, { + 'url': 'http://escapistmagazine.com/videos/view/the-escapist-presents/6618', + 'only_matching': True, + }, { + 'url': 'https://v1.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - uploader_id = self._html_search_regex( - r"

(.*?)", - webpage, 'uploader', fatal=False) - description = self._html_search_meta('description', webpage) - - raw_title = self._html_search_meta('title', webpage, fatal=True) - title = raw_title.partition(' : ')[2] - - player_url = self._og_search_video_url(webpage, name='player URL') - config_url = compat_urllib_parse.unquote(self._search_regex( - r'config=(.*)$', player_url, 'config URL')) - - formats = [] - - def _add_format(name, cfgurl, quality): - config = self._download_json( - cfgurl, video_id, - 'Downloading ' + name + ' configuration', - 'Unable to download ' + name + ' configuration', - transform_source=js_to_json) - - playlist = config['playlist'] - formats.append({ - 'url': playlist[1]['url'], - 'format_id': name, - 'quality': quality, + ims_video = self._parse_json( + self._search_regex( + r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'), + video_id) + video_id = ims_video['videoID'] + key = ims_video['hash'] + + config = self._download_webpage( + 'http://www.escapistmagazine.com/videos/vidconfig.php', + video_id, 'Downloading video config', headers={ + 'Referer': url, + }, query={ + 'videoID': video_id, + 'hash': key, }) - _add_format('normal', config_url, quality=0) - hq_url = (config_url + - ('&hq=1' if '?' in config_url else config_url + '?hq=1')) - try: - _add_format('hq', hq_url, quality=1) - except ExtractorError: - pass # That's fine, we'll just use normal quality + data = self._parse_json(_decrypt_config(key, config), video_id) + + video_data = data['videoData'] + + title = clean_html(video_data['title']) + formats = [{ + 'url': video['src'], + 'format_id': '%s-%sp' % (determine_ext(video['src']), video['res']), + 'height': int_or_none(video.get('res')), + } for video in data['files']['videos']] self._sort_formats(formats) return { 'id': video_id, 'formats': formats, - 'uploader': uploader, - 'uploader_id': uploader_id, 'title': title, - 'thumbnail': self._og_search_thumbnail(webpage), - 'description': description, - 'player_url': player_url, + 'thumbnail': self._og_search_thumbnail(webpage) or data.get('poster'), + 'description': self._og_search_description(webpage), + 'duration': float_or_none(video_data.get('duration'), 1000), + 'uploader': video_data.get('publisher'), + 'series': video_data.get('show'), }