projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| 7d55b62f S |
1 | # coding: utf-8 |
| 2 | from __future__ import unicode_literals | |
| 3 | ||
| 7d55b62f S |
4 | |
| 5 | from .common import InfoExtractor | |
| 6 | from ..compat import ( | |
| 7 | compat_b64decode, | |
| 8 | compat_chr, | |
| 9 | ) | |
| 10 | from ..utils import int_or_none | |
| 11 | ||
| 12 | ||
| 13 | class PopcorntimesIE(InfoExtractor): | |
| 14 | _VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)' | |
| 15 | _TEST = { | |
| 16 | 'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy', | |
| 17 | 'md5': '93f210991ad94ba8c3485950a2453257', | |
| 18 | 'info_dict': { | |
| 19 | 'id': 'A1XCFvz', | |
| 20 | 'display_id': 'haensel-und-gretel-opera-fantasy', | |
| 21 | 'ext': 'mp4', | |
| 22 | 'title': 'Hänsel und Gretel', | |
| 23 | 'description': 'md5:1b8146791726342e7b22ce8125cf6945', | |
| 24 | 'thumbnail': r're:^https?://.*\.jpg$', | |
| 25 | 'creator': 'John Paul', | |
| 26 | 'release_date': '19541009', | |
| 27 | 'duration': 4260, | |
| 28 | 'tbr': 5380, | |
| 29 | 'width': 720, | |
| 30 | 'height': 540, | |
| 31 | }, | |
| 32 | } | |
| 33 | ||
| 34 | def _real_extract(self, url): | |
| 5ad28e7f | 35 | mobj = self._match_valid_url(url) |
| 7d55b62f S |
36 | video_id, display_id = mobj.group('id', 'display_id') |
| 37 | ||
| 38 | webpage = self._download_webpage(url, display_id) | |
| 39 | ||
| 40 | title = self._search_regex( | |
| 41 | r'<h1>([^<]+)', webpage, 'title', | |
| 42 | default=None) or self._html_search_meta( | |
| 43 | 'ya:ovs:original_name', webpage, 'title', fatal=True) | |
| 44 | ||
| 45 | loc = self._search_regex( | |
| 46 | r'PCTMLOC\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'loc', | |
| 47 | group='value') | |
| 48 | ||
| 49 | loc_b64 = '' | |
| 50 | for c in loc: | |
| 51 | c_ord = ord(c) | |
| 52 | if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'): | |
| 53 | upper = ord('Z') if c_ord <= ord('Z') else ord('z') | |
| 54 | c_ord += 13 | |
| 55 | if upper < c_ord: | |
| 56 | c_ord -= 26 | |
| 57 | loc_b64 += compat_chr(c_ord) | |
| 58 | ||
| 59 | video_url = compat_b64decode(loc_b64).decode('utf-8') | |
| 60 | ||
| 61 | description = self._html_search_regex( | |
| 62 | r'(?s)<div[^>]+class=["\']pt-movie-desc[^>]+>(.+?)</div>', webpage, | |
| 63 | 'description', fatal=False) | |
| 64 | ||
| 65 | thumbnail = self._search_regex( | |
| 66 | r'<img[^>]+class=["\']video-preview[^>]+\bsrc=(["\'])(?P<value>(?:(?!\1).)+)\1', | |
| 67 | webpage, 'thumbnail', default=None, | |
| 68 | group='value') or self._og_search_thumbnail(webpage) | |
| 69 | ||
| 70 | creator = self._html_search_meta( | |
| 71 | 'video:director', webpage, 'creator', default=None) | |
| 72 | ||
| 73 | release_date = self._html_search_meta( | |
| 74 | 'video:release_date', webpage, default=None) | |
| 75 | if release_date: | |
| 76 | release_date = release_date.replace('-', '') | |
| 77 | ||
| 78 | def int_meta(name): | |
| 79 | return int_or_none(self._html_search_meta( | |
| 80 | name, webpage, default=None)) | |
| 81 | ||
| 82 | return { | |
| 83 | 'id': video_id, | |
| 84 | 'display_id': display_id, | |
| 85 | 'url': video_url, | |
| 86 | 'title': title, | |
| 87 | 'description': description, | |
| 88 | 'thumbnail': thumbnail, | |
| 89 | 'creator': creator, | |
| 90 | 'release_date': release_date, | |
| 91 | 'duration': int_meta('video:duration'), | |
| 92 | 'tbr': int_meta('ya:ovs:bitrate'), | |
| 93 | 'width': int_meta('og:video:width'), | |
| 94 | 'height': int_meta('og:video:height'), | |
| 95 | 'http_headers': { | |
| 96 | 'Referer': url, | |
| 97 | }, | |
| 98 | } |