From efc57145c10bdf22da9d8571c35ccd0404e3b7c3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 3 Sep 2017 17:30:02 +0700 Subject: [PATCH] [manyvids] Improve (closes #14059) --- youtube_dl/extractor/manyvids.py | 38 +++++++++++++++++++++----------- 1 file changed, 25 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/manyvids.py b/youtube_dl/extractor/manyvids.py index ea739ce3f..b94b3c2ab 100644 --- a/youtube_dl/extractor/manyvids.py +++ b/youtube_dl/extractor/manyvids.py @@ -2,35 +2,47 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote +from ..utils import int_or_none class ManyVidsIE(InfoExtractor): - _VALID_URL = r'https?://www.manyvids\.com/Video/(?P[0-9]+)' + _VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P\d+)' _TEST = { 'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/', 'md5': '03f11bb21c52dd12a05be21a5c7dcc97', 'info_dict': { 'id': '133957', 'ext': 'mp4', - 'title': 'everthing about me', - - } + 'title': 'everthing about me (Preview)', + 'view_count': int, + 'like_count': int, + }, } def _real_extract(self, url): - formats = [] video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - video_url = compat_urllib_parse_unquote(self._search_regex( - r'data-video-filepath=\"(.+?)\"', webpage, 'video URL', default='')) - title = self._html_search_regex(r']+class="m-a-0"[^>]*>([^<]+)', webpage, 'title') - formats.append({ - 'url': video_url - }) + video_url = self._search_regex( + r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'video URL', group='url') + + title = '%s (Preview)' % self._html_search_regex( + r']+class="m-a-0"[^>]*>([^<]+)', webpage, 'title') + + like_count = int_or_none(self._search_regex( + r'data-likes=["\'](\d+)', webpage, 'like count', default=None)) + view_count = int_or_none(self._html_search_regex( + r'(?s)]+class="views-wrapper"[^>]*>(.+?)