X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/46113edab215c2211a604c06245c16d5d4e57dcf..fe979149c83b5a935f7d28baf75848a9137316fd:/youtube_dl/extractor/tube8.py?ds=inline diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 64a1e90..1d9271d 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -1,13 +1,12 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - compat_urllib_parse_urlparse, - compat_urllib_request, int_or_none, + sanitized_Request, str_to_int, ) from ..aes import aes_decrypt_text @@ -15,79 +14,90 @@ from ..aes import aes_decrypt_text class Tube8IE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P[^/]+)/(?P\d+)' - _TESTS = [ - { - 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', - 'md5': '44bf12b98313827dd52d35b8706a4ea0', - 'info_dict': { - 'id': '229795', - 'display_id': 'kasia-music-video', - 'ext': 'mp4', - 'description': 'hot teen Kasia grinding', - 'uploader': 'unknown', - 'title': 'Kasia music video', - 'age_limit': 18, - } - }, - { - 'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/', - 'only_matching': True, - }, - ] + _TESTS = [{ + 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', + 'md5': '65e20c48e6abff62ed0c3965fff13a39', + 'info_dict': { + 'id': '229795', + 'display_id': 'kasia-music-video', + 'ext': 'mp4', + 'description': 'hot teen Kasia grinding', + 'uploader': 'unknown', + 'title': 'Kasia music video', + 'age_limit': 18, + 'duration': 230, + } + }, { + 'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') display_id = mobj.group('display_id') - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, display_id) - flashvars = json.loads(self._html_search_regex( - r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars')) + flashvars = self._parse_json( + self._search_regex( + r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'), + video_id) - video_url = flashvars['video_url'] - if flashvars.get('encrypted') is True: - video_url = aes_decrypt_text(video_url, flashvars['video_title'], 32).decode('utf-8') - path = compat_urllib_parse_urlparse(video_url).path - format_id = '-'.join(path.split('/')[4].split('_')[:2]) + formats = [] + for key, video_url in flashvars.items(): + if not isinstance(video_url, compat_str) or not video_url.startswith('http'): + continue + height = self._search_regex( + r'quality_(\d+)[pP]', key, 'height', default=None) + if not height: + continue + if flashvars.get('encrypted') is True: + video_url = aes_decrypt_text( + video_url, flashvars['video_title'], 32).decode('utf-8') + formats.append({ + 'url': video_url, + 'format_id': '%sp' % height, + 'height': int(height), + }) + self._sort_formats(formats) thumbnail = flashvars.get('image_url') title = self._html_search_regex( - r'videotitle\s*=\s*"([^"]+)', webpage, 'title') + r'videoTitle\s*=\s*"([^"]+)', webpage, 'title') description = self._html_search_regex( - r'>Description:(.+?)<', webpage, 'description', fatal=False) + r'>Description:\s*(.+?)\s*<', webpage, 'description', fatal=False) uploader = self._html_search_regex( - r'(?:)?([^<]+)(?:)?', + r'\s*(.+?)\s*<', webpage, 'uploader', fatal=False) + duration = int_or_none(flashvars.get('video_duration')) - like_count = int_or_none(self._html_search_regex( - r"rupVar\s*=\s*'(\d+)'", webpage, 'like count', fatal=False)) - dislike_count = int_or_none(self._html_search_regex( - r"rdownVar\s*=\s*'(\d+)'", webpage, 'dislike count', fatal=False)) - view_count = self._html_search_regex( - r'Views: ([\d,\.]+)', webpage, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) - comment_count = self._html_search_regex( - r'(\d+)', webpage, 'comment count', fatal=False) - if comment_count: - comment_count = str_to_int(comment_count) + like_count = int_or_none(self._search_regex( + r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False)) + dislike_count = int_or_none(self._search_regex( + r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False)) + view_count = str_to_int(self._search_regex( + r'Views: ([\d,\.]+)\s*', + webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._search_regex( + r'(\d+)', + webpage, 'comment count', fatal=False)) return { 'id': video_id, 'display_id': display_id, - 'url': video_url, 'title': title, 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, - 'format_id': format_id, + 'duration': duration, 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, 'age_limit': 18, + 'formats': formats, }