X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnormalboots.py;h=6aa0895b82e5949657a62b009addc8e93885936e;hp=8da289d7895134161271443be8e355eab043348b;hb=dcdb292fddc82ae11f4c0b647815a45c88a6b6d5;hpb=3bf8bc7f3753aef5fbd46b840b334e82ae409e4e diff --git a/youtube_dl/extractor/normalboots.py b/youtube_dl/extractor/normalboots.py index 8da289d78..6aa0895b8 100644 --- a/youtube_dl/extractor/normalboots.py +++ b/youtube_dl/extractor/normalboots.py @@ -1,61 +1,56 @@ -import re +# coding: utf-8 +from __future__ import unicode_literals from .common import InfoExtractor +from .screenwavemedia import ScreenwaveMediaIE from ..utils import ( - ExtractorError, unified_strdate, ) + class NormalbootsIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?normalboots\.com/video/(?P[0-9a-z-]*)/?$' + _VALID_URL = r'https?://(?:www\.)?normalboots\.com/video/(?P[0-9a-z-]*)/?$' _TEST = { - u'url': u'http://normalboots.com/video/home-alone-games-jontron/', - u'file': u'JonTronShow-52e2fafa8718e_high.mp4', - u'md5': u'8b215e2e0168c6081a1cf84b2846a2b5', - u'info_dict': { - u'title': u'Home Alone Games - JonTron - NormalBoots', - u'description': u'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Micha Frar for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for \u2018Tense Battle Theme\u2019:\xa0http://www.youtube.com/Kiamet/', - u'uploader': u'JonTron', - u'upload_date': u'20140125', - } + 'url': 'http://normalboots.com/video/home-alone-games-jontron/', + 'info_dict': { + 'id': 'home-alone-games-jontron', + 'ext': 'mp4', + 'title': 'Home Alone Games - JonTron - NormalBoots', + 'description': 'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for ‘Tense Battle Theme’:\xa0http://www.youtube.com/Kiamet/', + 'uploader': 'JonTron', + 'upload_date': '20140125', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'add_ie': ['ScreenwaveMedia'], } - + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group('videoid') - - info = { + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_uploader = self._html_search_regex( + r'Posted\sby\s(?P[A-Za-z]*)\s', + webpage, 'uploader', fatal=False) + video_upload_date = unified_strdate(self._html_search_regex( + r'[A-Za-z]+, (?P.*)', + webpage, 'date', fatal=False)) + + screenwavemedia_url = self._html_search_regex( + ScreenwaveMediaIE.EMBED_PATTERN, webpage, 'screenwave URL', + group='url') + + return { + '_type': 'url_transparent', 'id': video_id, - 'uploader': None, - 'upload_date': None, + 'url': screenwavemedia_url, + 'ie_key': ScreenwaveMediaIE.ie_key(), + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'uploader': video_uploader, + 'upload_date': video_upload_date, } - - if url[:4] != 'http': - url = 'http://' + url - - webpage = self._download_webpage(url, video_id) - video_title = self._og_search_title(webpage) - video_description = self._og_search_description(webpage) - video_thumbnail = self._og_search_thumbnail(webpage) - video_uploader = self._html_search_regex(r'Posted\sby\s(?P[A-Za-z]*)\s', - webpage, 'uploader') - raw_upload_date = self._html_search_regex('[A-Za-z]+, (?P.*)', - webpage, 'date') - video_upload_date = unified_strdate(raw_upload_date) - video_upload_date = unified_strdate(raw_upload_date) - - player_url = self._html_search_regex(r'[\S]+)"', webpage, 'url') - player_page = self._download_webpage(player_url, video_id) - video_url = u'http://player.screenwavemedia.com/' + self._html_search_regex(r"'file':\s'(?P[0-9A-Za-z-_\.]+)'", player_page, 'file') - - info['url'] = video_url - info['title'] = video_title - info['description'] = video_description - info['thumbnail'] = video_thumbnail - info['uploader'] = video_uploader - info['upload_date'] = video_upload_date - - return info