X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fbeeg.py;h=1086d76324a1df1484adb042f74b35a614fea01b;hb=2f483bc1c389709623117079439708783122b5ec;hp=34c2a756fba11f81516e87e095ef1e02d5e65417;hpb=e9bd0f772b28176e86cfe8c641b6281a96be2ee4;p=youtube-dl diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index 34c2a756f..1086d7632 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -1,14 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_chr, - compat_ord, - compat_urllib_parse_unquote, -) +from ..compat import compat_str from ..utils import ( int_or_none, - parse_iso8601, + unified_timestamp, ) @@ -16,7 +12,7 @@ class BeegIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P\d+)' _TEST = { 'url': 'http://beeg.com/5416503', - 'md5': '46c384def73b33dbc581262e5ee67cef', + 'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820', 'info_dict': { 'id': '5416503', 'ext': 'mp4', @@ -33,39 +29,19 @@ class BeegIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - video = self._download_json( - 'https://api.beeg.com/api/v5/video/%s' % video_id, video_id) - - def split(o, e): - def cut(s, x): - n.append(s[:x]) - return s[x:] - n = [] - r = len(o) % e - if r > 0: - o = cut(o, r) - while len(o) > e: - o = cut(o, e) - n.append(o) - return n + webpage = self._download_webpage(url, video_id) - def decrypt_key(key): - # Reverse engineered from http://static.beeg.com/cpl/1105.js - a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB' - e = compat_urllib_parse_unquote(key) - o = ''.join([ - compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21) - for n in range(len(e))]) - return ''.join(split(o, 3)[::-1]) + beeg_version = self._search_regex( + r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version', + default='1546225636701') - def decrypt_url(encrypted_url): - encrypted_url = self._proto_relative_url( - encrypted_url.replace('{DATA_MARKERS}', ''), 'https:') - key = self._search_regex( - r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None) - if not key: - return encrypted_url - return encrypted_url.replace(key, decrypt_key(key)) + for api_path in ('', 'api.'): + video = self._download_json( + 'https://%sbeeg.com/api/v6/%s/video/%s' + % (api_path, beeg_version, video_id), video_id, + fatal=api_path == 'api.') + if video: + break formats = [] for format_id, video_url in video.items(): @@ -76,18 +52,20 @@ class BeegIE(InfoExtractor): if not height: continue formats.append({ - 'url': decrypt_url(video_url), + 'url': self._proto_relative_url( + video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'), 'format_id': format_id, 'height': int(height), }) self._sort_formats(formats) title = video['title'] - video_id = video.get('id') or video_id + video_id = compat_str(video.get('id') or video_id) display_id = video.get('code') description = video.get('desc') + series = video.get('ps_name') - timestamp = parse_iso8601(video.get('date'), ' ') + timestamp = unified_timestamp(video.get('date')) duration = int_or_none(video.get('duration')) tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None @@ -97,9 +75,10 @@ class BeegIE(InfoExtractor): 'display_id': display_id, 'title': title, 'description': description, + 'series': series, 'timestamp': timestamp, 'duration': duration, 'tags': tags, 'formats': formats, - 'age_limit': 18, + 'age_limit': self._rta_search(webpage), }