projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| 9d46608e | 1 | import re |
| 2 | from .common import InfoExtractor | |
| 3 | from ..compat import compat_urlparse | |
| 4 | from ..utils import ( | |
| 5 | get_element_by_attribute, | |
| 6 | qualities, | |
| 7 | unescapeHTML, | |
| 8 | ) | |
| 9 | ||
| 10 | ||
| 11 | class OraTVIE(InfoExtractor): | |
| ca950f49 S |
12 | _VALID_URL = r'https?://(?:www\.)?(?:ora\.tv|unsafespeech\.com)/([^/]+/)*(?P<id>[^/\?#]+)' |
| 13 | _TESTS = [{ | |
| 9d46608e | 14 | 'url': 'https://www.ora.tv/larrykingnow/2015/12/16/vine-youtube-stars-zach-king-king-bach-on-their-viral-videos-0_36jupg6090pq', |
| 15 | 'md5': 'fa33717591c631ec93b04b0e330df786', | |
| 16 | 'info_dict': { | |
| 17 | 'id': '50178', | |
| 18 | 'ext': 'mp4', | |
| 19 | 'title': 'Vine & YouTube Stars Zach King & King Bach On Their Viral Videos!', | |
| 20 | 'description': 'md5:ebbc5b1424dd5dba7be7538148287ac1', | |
| 9d46608e | 21 | } |
| ca950f49 S |
22 | }, { |
| 23 | 'url': 'http://www.unsafespeech.com/video/2016/5/10/student-self-censorship-and-the-thought-police-on-university-campuses-0_6622bnkppw4d', | |
| 24 | 'only_matching': True, | |
| 25 | }] | |
| 9d46608e | 26 | |
| 27 | def _real_extract(self, url): | |
| 28 | display_id = self._match_id(url) | |
| 29 | webpage = self._download_webpage(url, display_id) | |
| 30 | ||
| ca950f49 S |
31 | video_data = self._search_regex( |
| 32 | r'"(?:video|current)"\s*:\s*({[^}]+?})', webpage, 'current video') | |
| 33 | m3u8_url = self._search_regex( | |
| 34 | r'hls_stream"?\s*:\s*"([^"]+)', video_data, 'm3u8 url', None) | |
| 9d46608e | 35 | if m3u8_url: |
| 36 | formats = self._extract_m3u8_formats( | |
| 37 | m3u8_url, display_id, 'mp4', 'm3u8_native', | |
| 38 | m3u8_id='hls', fatal=False) | |
| dfb1b146 | 39 | # similar to GameSpotIE |
| 9d46608e | 40 | m3u8_path = compat_urlparse.urlparse(m3u8_url).path |
| 41 | QUALITIES_RE = r'((,[a-z]+\d+)+,?)' | |
| 42 | available_qualities = self._search_regex( | |
| 43 | QUALITIES_RE, m3u8_path, 'qualities').strip(',').split(',') | |
| 44 | http_path = m3u8_path[1:].split('/', 1)[1] | |
| 45 | http_template = re.sub(QUALITIES_RE, r'%s', http_path) | |
| 46 | http_template = http_template.replace('.csmil/master.m3u8', '') | |
| 47 | http_template = compat_urlparse.urljoin( | |
| 48 | 'http://videocdn-pmd.ora.tv/', http_template) | |
| 49 | preference = qualities( | |
| 50 | ['mobile400', 'basic400', 'basic600', 'sd900', 'sd1200', 'sd1500', 'hd720', 'hd1080']) | |
| 51 | for q in available_qualities: | |
| 52 | formats.append({ | |
| 53 | 'url': http_template % q, | |
| 54 | 'format_id': q, | |
| f983b875 | 55 | 'quality': preference(q), |
| 9d46608e | 56 | }) |
| 9d46608e | 57 | else: |
| 58 | return self.url_result(self._search_regex( | |
| 59 | r'"youtube_id"\s*:\s*"([^"]+)', webpage, 'youtube id'), 'Youtube') | |
| 60 | ||
| 61 | return { | |
| ca950f49 S |
62 | 'id': self._search_regex( |
| 63 | r'"id"\s*:\s*(\d+)', video_data, 'video id', default=display_id), | |
| 9d46608e | 64 | 'display_id': display_id, |
| 65 | 'title': unescapeHTML(self._og_search_title(webpage)), | |
| 66 | 'description': get_element_by_attribute( | |
| 67 | 'class', 'video_txt_decription', webpage), | |
| ca950f49 S |
68 | 'thumbnail': self._proto_relative_url(self._search_regex( |
| 69 | r'"thumb"\s*:\s*"([^"]+)', video_data, 'thumbnail', None)), | |
| 9d46608e | 70 | 'formats': formats, |
| 71 | } |