projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| 6127693e PH |
1 | from .common import InfoExtractor |
| 2 | from ..compat import compat_parse_qs | |
| 3 | from ..utils import ( | |
| 4 | int_or_none, | |
| 5 | parse_duration, | |
| 6 | parse_iso8601, | |
| 7 | xpath_text, | |
| 8 | ) | |
| 9 | ||
| 10 | ||
| 11 | class FolketingetIE(InfoExtractor): | |
| 12 | IE_DESC = 'Folketinget (ft.dk; Danish parliament)' | |
| 13 | _VALID_URL = r'https?://(?:www\.)?ft\.dk/webtv/video/[^?#]*?\.(?P<id>[0-9]+)\.aspx' | |
| 14 | _TEST = { | |
| 15 | 'url': 'http://www.ft.dk/webtv/video/20141/eru/td.1165642.aspx?as=1#player', | |
| e1ccc04e | 16 | 'md5': '6269e8626fa1a891bf5369b386ae996a', |
| 6127693e PH |
17 | 'info_dict': { |
| 18 | 'id': '1165642', | |
| 19 | 'ext': 'mp4', | |
| 20 | 'title': 'Åbent samråd i Erhvervsudvalget', | |
| 21 | 'description': 'Åbent samråd med erhvervs- og vækstministeren om regeringens politik på teleområdet', | |
| 22 | 'view_count': int, | |
| 23 | 'width': 768, | |
| 24 | 'height': 432, | |
| 25 | 'tbr': 928000, | |
| 26 | 'timestamp': 1416493800, | |
| 27 | 'upload_date': '20141120', | |
| 28 | 'duration': 3960, | |
| 29 | }, | |
| dc95bd50 S |
30 | 'params': { |
| 31 | # rtmp download | |
| 32 | 'skip_download': True, | |
| 33 | }, | |
| 6127693e PH |
34 | } |
| 35 | ||
| 36 | def _real_extract(self, url): | |
| 37 | video_id = self._match_id(url) | |
| 38 | webpage = self._download_webpage(url, video_id) | |
| 39 | ||
| 40 | title = self._og_search_title(webpage) | |
| 41 | description = self._html_search_regex( | |
| 42 | r'(?s)<div class="video-item-agenda"[^>]*>(.*?)<', | |
| 43 | webpage, 'description', fatal=False) | |
| 44 | ||
| 45 | player_params = compat_parse_qs(self._search_regex( | |
| 46 | r'<embed src="http://ft\.arkena\.tv/flash/ftplayer\.swf\?([^"]+)"', | |
| 47 | webpage, 'player params')) | |
| 48 | xml_url = player_params['xml'][0] | |
| 49 | doc = self._download_xml(xml_url, video_id) | |
| 50 | ||
| 51 | timestamp = parse_iso8601(xpath_text(doc, './/date')) | |
| 52 | duration = parse_duration(xpath_text(doc, './/duration')) | |
| 53 | width = int_or_none(xpath_text(doc, './/width')) | |
| 54 | height = int_or_none(xpath_text(doc, './/height')) | |
| 55 | view_count = int_or_none(xpath_text(doc, './/views')) | |
| 56 | ||
| 57 | formats = [{ | |
| 58 | 'format_id': n.attrib['bitrate'], | |
| 59 | 'url': xpath_text(n, './url', fatal=True), | |
| 60 | 'tbr': int_or_none(n.attrib['bitrate']), | |
| 61 | } for n in doc.findall('.//streams/stream')] | |
| 6127693e PH |
62 | |
| 63 | return { | |
| 64 | 'id': video_id, | |
| 65 | 'title': title, | |
| 66 | 'formats': formats, | |
| 67 | 'description': description, | |
| 68 | 'timestamp': timestamp, | |
| 69 | 'width': width, | |
| 70 | 'height': height, | |
| 71 | 'duration': duration, | |
| 72 | 'view_count': view_count, | |
| 73 | } |