From a0a477b885dc1dd688058924357c4935f3c935cf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 30 Jul 2017 15:48:22 +0700 Subject: [PATCH] [youjizz] Fix extraction (closes #13744) --- youtube_dl/extractor/youjizz.py | 78 ++++++++++++++++++++++++++++----- 1 file changed, 67 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index b50f34e9b..f33fabe19 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -1,39 +1,95 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + determine_ext, + int_or_none, + parse_duration, +) class YouJizzIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]+)?-(?P[0-9]+)\.html(?:$|[?#])' + _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]*-(?P\d+)\.html|embed/(?P\d+))' _TESTS = [{ 'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html', - 'md5': '78fc1901148284c69af12640e01c6310', + 'md5': 'b1e1dfaa8bb9537d8b84eeda9cf4acf4', 'info_dict': { 'id': '2189178', 'ext': 'mp4', 'title': 'Zeichentrick 1', 'age_limit': 18, + 'duration': 2874, } }, { 'url': 'http://www.youjizz.com/videos/-2189178.html', 'only_matching': True, + }, { + 'url': 'https://www.youjizz.com/videos/embed/31991001', + 'only_matching': True, }] def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') or mobj.group('embed_id') + webpage = self._download_webpage(url, video_id) - # YouJizz's HTML5 player has invalid HTML - webpage = webpage.replace('"controls', '" controls') - age_limit = self._rta_search(webpage) - video_title = self._html_search_regex( - r'\s*(.*)\s*', webpage, 'title') - info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0] + title = self._html_search_regex( + r'(.+?)', webpage, 'title') + + formats = [] + + encodings = self._parse_json( + self._search_regex( + r'encodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings', + default='[]'), + video_id, fatal=False) + for encoding in encodings: + if not isinstance(encoding, dict): + continue + format_url = encoding.get('filename') + if not isinstance(format_url, compat_str): + continue + if determine_ext(format_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + else: + format_id = encoding.get('name') or encoding.get('quality') + height = int_or_none(self._search_regex( + r'^(\d+)[pP]', format_id, 'height', default=None)) + formats.append({ + 'url': format_url, + 'format_id': format_id, + 'height': height, + }) + + if formats: + info_dict = { + 'formats': formats, + } + else: + # YouJizz's HTML5 player has invalid HTML + webpage = webpage.replace('"controls', '" controls') + info_dict = self._parse_html5_media_entries( + url, webpage, video_id)[0] + + duration = parse_duration(self._search_regex( + r'Runtime:([^<]+)', webpage, 'duration', + default=None)) + uploader = self._search_regex( + r'Uploaded By:.*?]*>([^<]+)', webpage, 'uploader', + default=None) info_dict.update({ 'id': video_id, - 'title': video_title, - 'age_limit': age_limit, + 'title': title, + 'age_limit': self._rta_search(webpage), + 'duration': duration, + 'uploader': uploader, }) return info_dict