projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| 2c0c9dc4 S |
1 | import re |
| 2 | ||
| 3 | from .common import InfoExtractor | |
| 4 | from ..utils import ( | |
| e897bd82 | 5 | find_xpath_attr, |
| 2c0c9dc4 S |
6 | int_or_none, |
| 7 | parse_iso8601, | |
| 2c0c9dc4 | 8 | xpath_text, |
| e897bd82 | 9 | xpath_with_ns, |
| 2c0c9dc4 S |
10 | ) |
| 11 | ||
| 12 | ||
| 13 | class XstreamIE(InfoExtractor): | |
| 14 | _VALID_URL = r'''(?x) | |
| 15 | (?: | |
| 16 | xstream:| | |
| 17 | https?://frontend\.xstream\.(?:dk|net)/ | |
| 18 | ) | |
| 19 | (?P<partner_id>[^/]+) | |
| 20 | (?: | |
| 21 | :| | |
| 22 | /feed/video/\?.*?\bid= | |
| 23 | ) | |
| 24 | (?P<id>\d+) | |
| 25 | ''' | |
| 26 | _TESTS = [{ | |
| 27 | 'url': 'http://frontend.xstream.dk/btno/feed/video/?platform=web&id=86588', | |
| 28 | 'md5': 'd7d17e3337dc80de6d3a540aefbe441b', | |
| 29 | 'info_dict': { | |
| 30 | 'id': '86588', | |
| 31 | 'ext': 'mov', | |
| 32 | 'title': 'Otto Wollertsen', | |
| 33 | 'description': 'Vestlendingen Otto Fredrik Wollertsen', | |
| 34 | 'timestamp': 1430473209, | |
| 35 | 'upload_date': '20150501', | |
| 36 | }, | |
| 37 | }, { | |
| 38 | 'url': 'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=21039', | |
| 39 | 'only_matching': True, | |
| 40 | }] | |
| 41 | ||
| d50116b8 | 42 | def _extract_video_info(self, partner_id, video_id): |
| 2c0c9dc4 S |
43 | data = self._download_xml( |
| 44 | 'http://frontend.xstream.dk/%s/feed/video/?platform=web&id=%s' | |
| 45 | % (partner_id, video_id), | |
| 46 | video_id) | |
| 47 | ||
| 48 | NS_MAP = { | |
| 49 | 'atom': 'http://www.w3.org/2005/Atom', | |
| 50 | 'xt': 'http://xstream.dk/', | |
| 51 | 'media': 'http://search.yahoo.com/mrss/', | |
| 52 | } | |
| 53 | ||
| 54 | entry = data.find(xpath_with_ns('./atom:entry', NS_MAP)) | |
| 55 | ||
| 56 | title = xpath_text( | |
| 57 | entry, xpath_with_ns('./atom:title', NS_MAP), 'title') | |
| 58 | description = xpath_text( | |
| 59 | entry, xpath_with_ns('./atom:summary', NS_MAP), 'description') | |
| 60 | timestamp = parse_iso8601(xpath_text( | |
| 61 | entry, xpath_with_ns('./atom:published', NS_MAP), 'upload date')) | |
| 62 | ||
| 63 | formats = [] | |
| 64 | media_group = entry.find(xpath_with_ns('./media:group', NS_MAP)) | |
| 65 | for media_content in media_group.findall(xpath_with_ns('./media:content', NS_MAP)): | |
| 66 | media_url = media_content.get('url') | |
| 67 | if not media_url: | |
| 68 | continue | |
| 69 | tbr = int_or_none(media_content.get('bitrate')) | |
| 70 | mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url) | |
| 71 | if mobj: | |
| 72 | formats.append({ | |
| 73 | 'url': mobj.group('url'), | |
| 74 | 'play_path': 'mp4:%s' % mobj.group('playpath'), | |
| 75 | 'app': mobj.group('app'), | |
| 76 | 'ext': 'flv', | |
| 77 | 'tbr': tbr, | |
| 78 | 'format_id': 'rtmp-%d' % tbr, | |
| 79 | }) | |
| 80 | else: | |
| 81 | formats.append({ | |
| 82 | 'url': media_url, | |
| 83 | 'tbr': tbr, | |
| 84 | }) | |
| 2c0c9dc4 S |
85 | |
| 86 | link = find_xpath_attr( | |
| 87 | entry, xpath_with_ns('./atom:link', NS_MAP), 'rel', 'original') | |
| 88 | if link is not None: | |
| 89 | formats.append({ | |
| 90 | 'url': link.get('href'), | |
| 91 | 'format_id': link.get('rel'), | |
| f983b875 | 92 | 'quality': 1, |
| 2c0c9dc4 S |
93 | }) |
| 94 | ||
| 95 | thumbnails = [{ | |
| 96 | 'url': splash.get('url'), | |
| 97 | 'width': int_or_none(splash.get('width')), | |
| 98 | 'height': int_or_none(splash.get('height')), | |
| 99 | } for splash in media_group.findall(xpath_with_ns('./xt:splash', NS_MAP))] | |
| 100 | ||
| 101 | return { | |
| 102 | 'id': video_id, | |
| 103 | 'title': title, | |
| 104 | 'description': description, | |
| 105 | 'timestamp': timestamp, | |
| 106 | 'formats': formats, | |
| 107 | 'thumbnails': thumbnails, | |
| 108 | } | |
| d50116b8 | 109 | |
| 110 | def _real_extract(self, url): | |
| 5ad28e7f | 111 | mobj = self._match_valid_url(url) |
| d50116b8 | 112 | partner_id = mobj.group('partner_id') |
| 113 | video_id = mobj.group('id') | |
| 114 | ||
| 115 | return self._extract_video_info(partner_id, video_id) |