X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/e76f531201cd41dfc0ce00be28bcc5c575c7acc5..7b54e7278c1ff62e888689ec470f488682311356:/youtube_dl/extractor/beeg.py diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index 61bc2f7..5788d13 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -1,17 +1,22 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urlparse, +) from ..utils import ( int_or_none, - parse_iso8601, + unified_timestamp, ) class BeegIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P\d+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P\d+)' + _TESTS = [{ + # api/v6 v1 'url': 'http://beeg.com/5416503', - 'md5': '46c384def73b33dbc581262e5ee67cef', + 'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820', 'info_dict': { 'id': '5416503', 'ext': 'mp4', @@ -23,13 +28,52 @@ class BeegIE(InfoExtractor): 'tags': list, 'age_limit': 18, } - } + }, { + # api/v6 v2 + 'url': 'https://beeg.com/1941093077?t=911-1391', + 'only_matching': True, + }, { + # api/v6 v2 w/o t + 'url': 'https://beeg.com/1277207756', + 'only_matching': True, + }, { + 'url': 'https://beeg.porn/video/5416503', + 'only_matching': True, + }, { + 'url': 'https://beeg.porn/5416503', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - video = self._download_json( - 'http://beeg.com/api/v1/video/%s' % video_id, video_id) + webpage = self._download_webpage(url, video_id) + + beeg_version = self._search_regex( + r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version', + default='1546225636701') + + if len(video_id) >= 10: + query = { + 'v': 2, + } + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + t = qs.get('t', [''])[0].split('-') + if len(t) > 1: + query.update({ + 's': t[0], + 'e': t[1], + }) + else: + query = {'v': 1} + + 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.', query=query) + if video: + break formats = [] for format_id, video_url in video.items(): @@ -40,18 +84,20 @@ class BeegIE(InfoExtractor): if not height: continue formats.append({ - 'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'), + '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 @@ -61,9 +107,10 @@ 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), }