projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| f58487b3 TV |
1 | from .common import InfoExtractor |
| 2 | from ..utils import escape_url | |
| 3 | ||
| 4 | import re | |
| 5 | ||
| 6 | class VierIE (InfoExtractor): | |
| 7 | _VALID_URL = r'(?:http://)?www.vier.be/(?P<program>.*)/videos/(.+?)/(?P<id>\d*)' | |
| 8 | _TEST = { | |
| 9 | 'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129', | |
| 10 | 'md5': 'bf48f4eb998cbde44ecd02fc42c51149', | |
| 11 | 'info_dict': { | |
| 12 | 'id': '16129', | |
| 13 | 'ext': 'mp4', | |
| 14 | 'title': 'Het wordt warm in De Moestuin', | |
| 15 | 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', | |
| 16 | }, | |
| 17 | } | |
| 18 | ||
| 19 | def _real_extract (self, url): | |
| 20 | mobj = re.match (self._VALID_URL, url) | |
| 21 | ||
| 22 | program = mobj.group ('program') | |
| 23 | video_id = mobj.group ('id') | |
| 24 | ||
| 25 | webpage = self._download_webpage (url, video_id) | |
| 26 | ||
| 27 | title = self._html_search_regex(r'<meta property="og:title" content="(.+?)" />', webpage, u'title') | |
| 28 | description = self._html_search_regex (r'<meta property="og:description" content="(.+?)" />', webpage, u'description') | |
| 29 | vod_id = self._html_search_regex(r'"filename" : "(.+?)"', webpage, u'playlist URL') | |
| 30 | url = escape_url ("http://vod.streamcloud.be/vier_vod/mp4:_definst_/" + vod_id + ".mp4/playlist.m3u8") | |
| 31 | ||
| 32 | return { | |
| 33 | 'id': video_id, | |
| 34 | 'title': title, | |
| 35 | 'description': description, | |
| 36 | 'formats': self._extract_m3u8_formats(url, video_id, 'mp4'), | |
| 37 | } | |
| 38 | ||
| 39 | class VierVideosIE (InfoExtractor): | |
| 40 | _VALID_URL = r'http://www.vier.be/(?P<program>.*)/videos(\?page=(?P<page>\d*))?$' | |
| 41 | _TESTS = [{ | |
| 42 | 'url': 'http://www.vier.be/demoestuin/videos', | |
| 43 | 'info_dict': { | |
| 44 | 'id': 'demoestuin page(0)', | |
| 45 | }, | |
| 46 | 'playlist_mincount': 20, | |
| 47 | }, | |
| 48 | { | |
| 49 | 'url': 'http://www.vier.be/demoestuin/videos?page=6', | |
| 50 | 'info_dict': { | |
| 51 | 'id': 'demoestuin page(6)', | |
| 52 | }, | |
| 53 | 'playlist_mincount': 20, | |
| 54 | }] | |
| 55 | ||
| 56 | def _real_extract (self, url): | |
| 57 | mobj = re.match (self._VALID_URL, url) | |
| 58 | ||
| 59 | program = mobj.group ('program') | |
| 60 | page = mobj.group ('page') | |
| 61 | if page == None: | |
| 62 | page = 0 | |
| 63 | ||
| 64 | videos_id = program + " page(" + str (page) + ")" | |
| 65 | videos_page = self._download_webpage (url, videos_id, note='Retrieving videos page') | |
| 66 | ||
| 67 | return { | |
| 68 | '_type': 'playlist', | |
| 69 | 'id': videos_id, | |
| 70 | 'entries': [{ | |
| 71 | '_type': 'url', | |
| 72 | 'url': "http://www.vier.be/" + eurl[0], | |
| 73 | 'ie_key': 'Vier', | |
| 74 | } for eurl in re.findall (r'<h3><a href="(.+?)">(.+?)</a></h3>', videos_page)] | |
| 75 | } |