projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| bbd5f2de | 1 | from __future__ import unicode_literals |
| 2 | ||
| bbd5f2de | 3 | from .common import InfoExtractor |
| 4 | ||
| 5 | ||
| 6 | class SexuIE(InfoExtractor): | |
| 7 | _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)' | |
| 8 | _TEST = { | |
| 9 | 'url': 'http://sexu.com/961791/', | |
| 10 | 'md5': 'ff615aca9691053c94f8f10d96cd7884', | |
| 11 | 'info_dict': { | |
| 12 | 'id': '961791', | |
| 13 | 'ext': 'mp4', | |
| 437f68d8 | 14 | 'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b', |
| c58e7406 | 15 | 'description': 'md5:2b75327061310a3afb3fbd7d09e2e403', |
| bbd5f2de | 16 | 'categories': list, # NSFW |
| ec85ded8 | 17 | 'thumbnail': r're:https?://.*\.jpg$', |
| bbd5f2de | 18 | 'age_limit': 18, |
| 19 | } | |
| 20 | } | |
| 21 | ||
| 22 | def _real_extract(self, url): | |
| 3fa5bb38 | 23 | video_id = self._match_id(url) |
| bbd5f2de | 24 | webpage = self._download_webpage(url, video_id) |
| 25 | ||
| e7bd1737 S |
26 | jwvideo = self._parse_json( |
| 27 | self._search_regex(r'\.setup\(\s*({.+?})\s*\);', webpage, 'jwvideo'), | |
| 28 | video_id) | |
| 29 | ||
| 30 | sources = jwvideo['sources'] | |
| 31 | ||
| bbd5f2de | 32 | formats = [{ |
| e7bd1737 S |
33 | 'url': source['file'].replace('\\', ''), |
| 34 | 'format_id': source.get('label'), | |
| f5521ea2 S |
35 | 'height': int(self._search_regex( |
| 36 | r'^(\d+)[pP]', source.get('label', ''), 'height', | |
| 37 | default=None)), | |
| e7bd1737 | 38 | } for source in sources if source.get('file')] |
| bbd5f2de | 39 | self._sort_formats(formats) |
| 40 | ||
| 41 | title = self._html_search_regex( | |
| 3fa5bb38 | 42 | r'<title>([^<]+)\s*-\s*Sexu\.Com</title>', webpage, 'title') |
| bbd5f2de | 43 | |
| 3fa5bb38 PH |
44 | description = self._html_search_meta( |
| 45 | 'description', webpage, 'description') | |
| bbd5f2de | 46 | |
| e7bd1737 | 47 | thumbnail = jwvideo.get('image') |
| bbd5f2de | 48 | |
| 3fa5bb38 PH |
49 | categories_str = self._html_search_meta( |
| 50 | 'keywords', webpage, 'categories') | |
| bbd5f2de | 51 | categories = ( |
| 52 | None if categories_str is None | |
| 53 | else categories_str.split(',')) | |
| 54 | ||
| 55 | return { | |
| 56 | 'id': video_id, | |
| 57 | 'title': title, | |
| 58 | 'description': description, | |
| 59 | 'thumbnail': thumbnail, | |
| 60 | 'categories': categories, | |
| 61 | 'formats': formats, | |
| 62 | 'age_limit': 18, | |
| 63 | } |