From 9aaaf8e8e8ae12ed8fbc62461558a4cdb8640ad5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 1 Apr 2016 23:47:27 +0600 Subject: [PATCH] [camwithher] Improve extraction (Closes #8989) --- youtube_dl/extractor/camwithher.py | 95 ++++++++++++++++++++---------- 1 file changed, 64 insertions(+), 31 deletions(-) diff --git a/youtube_dl/extractor/camwithher.py b/youtube_dl/extractor/camwithher.py index eb0a4ec56..9809096ec 100644 --- a/youtube_dl/extractor/camwithher.py +++ b/youtube_dl/extractor/camwithher.py @@ -1,55 +1,88 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, + unified_strdate, +) class CamWithHerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?camwithher\.tv/view_video\.php\?.*viewkey=(?P\w+)' + _VALID_URL = r'https?://(?:www\.)?camwithher\.tv/view_video\.php\?.*\bviewkey=(?P\w+)' - _TESTS = [ - { - 'url': 'http://camwithher.tv/view_video.php?viewkey=6e9a24e2c0e842e1f177&page=&viewtype=&category=', - 'info_dict': { - 'id': '5644', - 'ext': 'flv', - 'title': 'Periscope Tease', - }, - 'params': { - 'skip_download': True, - } + _TESTS = [{ + 'url': 'http://camwithher.tv/view_video.php?viewkey=6e9a24e2c0e842e1f177&page=&viewtype=&category=', + 'info_dict': { + 'id': '5644', + 'ext': 'flv', + 'title': 'Periscope Tease', + 'description': 'In the clouds teasing on periscope to my favorite song', + 'duration': 240, + 'view_count': int, + 'comment_count': int, + 'uploader': 'MileenaK', + 'upload_date': '20160322', }, - { - 'url': 'http://camwithher.tv/view_video.php?viewkey=6dfd8b7c97531a459937', - 'only_matching': True, - }, - { - 'url': 'http://camwithher.tv/view_video.php?page=&viewkey=6e9a24e2c0e842e1f177&viewtype=&category=', - 'only_matching': True, - }, - { - 'url': 'http://camwithher.tv/view_video.php?viewkey=b6c3b5bea9515d1a1fc4&page=&viewtype=&category=mv', - 'only_matching': True, + 'params': { + 'skip_download': True, } - ] + }, { + 'url': 'http://camwithher.tv/view_video.php?viewkey=6dfd8b7c97531a459937', + 'only_matching': True, + }, { + 'url': 'http://camwithher.tv/view_video.php?page=&viewkey=6e9a24e2c0e842e1f177&viewtype=&category=', + 'only_matching': True, + }, { + 'url': 'http://camwithher.tv/view_video.php?viewkey=b6c3b5bea9515d1a1fc4&page=&viewtype=&category=mv', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - flv_id = self._html_search_regex(r' 2010 else flv_id) + # Video URL construction algorithm is reverse-engineered from cwhplayer.swf + rtmp_url = 'rtmp://camwithher.tv/clipshare/%s' % ( + ('mp4:%s.mp4' % flv_id) if int(flv_id) > 2010 else flv_id) + + title = self._html_search_regex( + r']+style="float:left"[^>]*>\s*

(.+?)

', webpage, 'title') + description = self._html_search_regex( + r'>Description:(.+?)', webpage, 'description', default=None) + + runtime = self._search_regex( + r'Runtime\s*:\s*(.+?) \|', webpage, 'duration', default=None) + if runtime: + runtime = re.sub(r'[\s-]', '', runtime) + duration = parse_duration(runtime) + view_count = int_or_none(self._search_regex( + r'Views\s*:\s*(\d+)', webpage, 'view count', default=None)) + comment_count = int_or_none(self._search_regex( + r'Comments\s*:\s*(\d+)', webpage, 'comment count', default=None)) + + uploader = self._search_regex( + r'Added by\s*:\s*]+>([^<]+)
', webpage, 'uploader', default=None) + upload_date = unified_strdate(self._search_regex( + r'Added on\s*:\s*([\d-]+)', webpage, 'upload date', default=None)) - title = self._html_search_regex(r'
\s+

(.+?)

', webpage, 'title') return { 'id': flv_id, 'url': rtmp_url, - 'no_resume': True, 'ext': 'flv', + 'no_resume': True, 'title': title, + 'description': description, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count, + 'uploader': uploader, + 'upload_date': upload_date, }