projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| 0eb799ba JMF |
1 | from __future__ import unicode_literals |
| 2 | ||
| bfd5c93a | 3 | import json |
| 78af8eb1 PH |
4 | import re |
| 5 | ||
| 6 | from .common import InfoExtractor | |
| 74ac9bdd JMF |
7 | from ..utils import ( |
| 8 | compat_urlparse, | |
| a921f407 | 9 | get_meta_content, |
| 74ac9bdd | 10 | ) |
| 78af8eb1 PH |
11 | |
| 12 | ||
| 13 | class UstreamIE(InfoExtractor): | |
| b702eceb | 14 | _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<videoID>\d+)' |
| 0eb799ba | 15 | IE_NAME = 'ustream' |
| ca6aada4 | 16 | _TEST = { |
| 0eb799ba JMF |
17 | 'url': 'http://www.ustream.tv/recorded/20274954', |
| 18 | 'file': '20274954.flv', | |
| 19 | 'md5': '088f151799e8f572f84eb62f17d73e5c', | |
| 20 | 'info_dict': { | |
| 21 | "uploader": "Young Americans for Liberty", | |
| 22 | "title": "Young Americans for Liberty February 7, 2012 2:28 AM", | |
| 23 | }, | |
| 6f5ac90c | 24 | } |
| 78af8eb1 PH |
25 | |
| 26 | def _real_extract(self, url): | |
| 27 | m = re.match(self._VALID_URL, url) | |
| b702eceb | 28 | video_id = m.group('videoID') |
| 29 | ||
| 30 | if m.group('type') == 'embed/recorded': # some sites use this embed format (see: http://github.com/rg3/youtube-dl/issues/2990) | |
| 31 | video_id = m.group('videoID') | |
| b702eceb | 32 | desktop_url = 'http://www.ustream.tv/recorded/' + video_id |
| 33 | return self.url_result(desktop_url, 'Ustream') | |
| 5c386252 | 34 | if m.group('type') == 'embed': |
| 35 | video_id = m.group('videoID') | |
| 36 | webpage = self._download_webpage(url, video_id) | |
| 37 | desktop_video_id = self._html_search_regex(r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id') | |
| 38 | desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id | |
| 39 | return self.url_result(desktop_url, 'Ustream') | |
| 40 | ||
| 0eb799ba | 41 | video_url = 'http://tcdn.ustream.tv/video/%s' % video_id |
| 78af8eb1 PH |
42 | webpage = self._download_webpage(url, video_id) |
| 43 | ||
| 44 | self.report_extraction(video_id) | |
| 45 | ||
| 46 | video_title = self._html_search_regex(r'data-title="(?P<title>.+)"', | |
| 0eb799ba | 47 | webpage, 'title') |
| 78af8eb1 PH |
48 | |
| 49 | uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>', | |
| 0eb799ba | 50 | webpage, 'uploader', fatal=False, flags=re.DOTALL) |
| 78af8eb1 PH |
51 | |
| 52 | thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"', | |
| 0eb799ba JMF |
53 | webpage, 'thumbnail', fatal=False) |
| 54 | ||
| 55 | return { | |
| 56 | 'id': video_id, | |
| 57 | 'url': video_url, | |
| 58 | 'ext': 'flv', | |
| 59 | 'title': video_title, | |
| 60 | 'uploader': uploader, | |
| 61 | 'thumbnail': thumbnail, | |
| 62 | } | |
| 63 | ||
| bfd5c93a | 64 | |
| bfd5c93a | 65 | class UstreamChannelIE(InfoExtractor): |
| 66 | _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)' | |
| 0eb799ba | 67 | IE_NAME = 'ustream:channel' |
| bfd5c93a | 68 | |
| 69 | def _real_extract(self, url): | |
| 70 | m = re.match(self._VALID_URL, url) | |
| 71 | slug = m.group('slug') | |
| a921f407 JMF |
72 | webpage = self._download_webpage(url, slug) |
| 73 | channel_id = get_meta_content('ustream:channel_id', webpage) | |
| bfd5c93a | 74 | |
| bfd5c93a | 75 | BASE = 'http://www.ustream.tv' |
| 76 | next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id | |
| a921f407 | 77 | video_ids = [] |
| bfd5c93a | 78 | while next_url: |
| 74ac9bdd | 79 | reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id)) |
| a921f407 | 80 | video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data'])) |
| bfd5c93a | 81 | next_url = reply['nextUrl'] |
| bfd5c93a | 82 | |
| bfd5c93a | 83 | urls = ['http://www.ustream.tv/recorded/' + vid for vid in video_ids] |
| 84 | url_entries = [self.url_result(eurl, 'Ustream') for eurl in urls] | |
| 74ac9bdd | 85 | return self.playlist_result(url_entries, channel_id) |