X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/099764c0c91f4ad7db03d9347798f8619383ea7e..a7fd25993be110e616bb9bf6d602949b54df1a7d:/youtube_dl/extractor/wimp.py diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index d6dec25..ea234e3 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -1,55 +1,54 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from .youtube import YoutubeIE class WimpIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/' + _VALID_URL = r'https?://(?:www\.)?wimp\.com/(?P[^/]+)' _TESTS = [{ - 'url': 'http://www.wimp.com/maruexhausted/', - 'md5': 'f1acced123ecb28d9bb79f2479f2b6a1', + 'url': 'http://www.wimp.com/maru-is-exhausted/', + 'md5': 'ee21217ffd66d058e8b16be340b74883', 'info_dict': { - 'id': 'maruexhausted', - 'ext': 'flv', + 'id': 'maru-is-exhausted', + 'ext': 'mp4', 'title': 'Maru is exhausted.', 'description': 'md5:57e099e857c0a4ea312542b684a869b8', } }, { - # youtube video 'url': 'http://www.wimp.com/clowncar/', + 'md5': '5c31ad862a90dc5b1f023956faec13fe', 'info_dict': { 'id': 'cG4CEr2aiSg', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Basset hound clown car...incredible!', - 'description': 'md5:8d228485e0719898c017203f900b3a35', + 'description': '5 of my Bassets crawled in this dog loo! www.bellinghambassets.com\n\nFor licensing/usage please contact: licensing(at)jukinmediadotcom', + 'upload_date': '20140303', 'uploader': 'Gretchen Hoey', 'uploader_id': 'gretchenandjeff1', - 'upload_date': '20140303', }, 'add_ie': ['Youtube'], }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - video_url = self._search_regex( - r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", webpage, 'video URL') - if YoutubeIE.suitable(video_url): - self.to_screen('Found YouTube video') - return { - '_type': 'url', - 'url': video_url, - 'ie_key': YoutubeIE.ie_key(), - } - - return { + + youtube_id = self._search_regex( + (r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']", + r'data-id=["\']([0-9A-Za-z_-]{11})'), + webpage, 'video URL', default=None) + if youtube_id: + return self.url_result(youtube_id, YoutubeIE.ie_key()) + + info_dict = self._extract_jwplayer_data( + webpage, video_id, require_title=False) + + info_dict.update({ 'id': video_id, - 'url': video_url, 'title': self._og_search_title(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), - } + }) + + return info_dict