You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

75 lines
3.2 KiB

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import re
  4. from .common import InfoExtractor
  5. from ..compat import compat_urlparse
  6. from ..utils import (
  7. get_element_by_attribute,
  8. qualities,
  9. unescapeHTML,
  10. )
  11. class OraTVIE(InfoExtractor):
  12. _VALID_URL = r'https?://(?:www\.)?(?:ora\.tv|unsafespeech\.com)/([^/]+/)*(?P<id>[^/\?#]+)'
  13. _TESTS = [{
  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',
  21. }
  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. }]
  26. def _real_extract(self, url):
  27. display_id = self._match_id(url)
  28. webpage = self._download_webpage(url, display_id)
  29. video_data = self._search_regex(
  30. r'"(?:video|current)"\s*:\s*({[^}]+?})', webpage, 'current video')
  31. m3u8_url = self._search_regex(
  32. r'hls_stream"?\s*:\s*"([^"]+)', video_data, 'm3u8 url', None)
  33. if m3u8_url:
  34. formats = self._extract_m3u8_formats(
  35. m3u8_url, display_id, 'mp4', 'm3u8_native',
  36. m3u8_id='hls', fatal=False)
  37. # similar to GameSpotIE
  38. m3u8_path = compat_urlparse.urlparse(m3u8_url).path
  39. QUALITIES_RE = r'((,[a-z]+\d+)+,?)'
  40. available_qualities = self._search_regex(
  41. QUALITIES_RE, m3u8_path, 'qualities').strip(',').split(',')
  42. http_path = m3u8_path[1:].split('/', 1)[1]
  43. http_template = re.sub(QUALITIES_RE, r'%s', http_path)
  44. http_template = http_template.replace('.csmil/master.m3u8', '')
  45. http_template = compat_urlparse.urljoin(
  46. 'http://videocdn-pmd.ora.tv/', http_template)
  47. preference = qualities(
  48. ['mobile400', 'basic400', 'basic600', 'sd900', 'sd1200', 'sd1500', 'hd720', 'hd1080'])
  49. for q in available_qualities:
  50. formats.append({
  51. 'url': http_template % q,
  52. 'format_id': q,
  53. 'preference': preference(q),
  54. })
  55. self._sort_formats(formats)
  56. else:
  57. return self.url_result(self._search_regex(
  58. r'"youtube_id"\s*:\s*"([^"]+)', webpage, 'youtube id'), 'Youtube')
  59. return {
  60. 'id': self._search_regex(
  61. r'"id"\s*:\s*(\d+)', video_data, 'video id', default=display_id),
  62. 'display_id': display_id,
  63. 'title': unescapeHTML(self._og_search_title(webpage)),
  64. 'description': get_element_by_attribute(
  65. 'class', 'video_txt_decription', webpage),
  66. 'thumbnail': self._proto_relative_url(self._search_regex(
  67. r'"thumb"\s*:\s*"([^"]+)', video_data, 'thumbnail', None)),
  68. 'formats': formats,
  69. }