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.

210 lines
7.7 KiB

9 years ago
9 years ago
  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import json
  4. import re
  5. from .common import InfoExtractor
  6. from ..utils import (
  7. determine_ext,
  8. ExtractorError,
  9. float_or_none,
  10. int_or_none,
  11. parse_iso8601,
  12. sanitized_Request,
  13. )
  14. class ToggleIE(InfoExtractor):
  15. IE_NAME = 'toggle'
  16. _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)'
  17. _TESTS = [{
  18. 'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
  19. 'info_dict': {
  20. 'id': '343115',
  21. 'ext': 'mp4',
  22. 'title': 'Lion Moms Premiere',
  23. 'description': 'md5:aea1149404bff4d7f7b6da11fafd8e6b',
  24. 'upload_date': '20150910',
  25. 'timestamp': 1441858274,
  26. },
  27. 'params': {
  28. 'skip_download': 'm3u8 download',
  29. }
  30. }, {
  31. 'note': 'DRM-protected video',
  32. 'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413',
  33. 'info_dict': {
  34. 'id': '341413',
  35. 'ext': 'wvm',
  36. 'title': 'Dug\'s Special Mission',
  37. 'description': 'md5:e86c6f4458214905c1772398fabc93e0',
  38. 'upload_date': '20150827',
  39. 'timestamp': 1440644006,
  40. },
  41. 'params': {
  42. 'skip_download': 'DRM-protected wvm download',
  43. }
  44. }, {
  45. # this also tests correct video id extraction
  46. 'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
  47. 'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
  48. 'info_dict': {
  49. 'id': '332861',
  50. 'ext': 'mp4',
  51. 'title': '28th SEA Games (5 Show) - Episode 11',
  52. 'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa',
  53. 'upload_date': '20150605',
  54. 'timestamp': 1433480166,
  55. },
  56. 'params': {
  57. 'skip_download': 'DRM-protected wvm download',
  58. },
  59. 'skip': 'm3u8 links are geo-restricted'
  60. }, {
  61. 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
  62. 'only_matching': True,
  63. }, {
  64. 'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367',
  65. 'only_matching': True,
  66. }, {
  67. 'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
  68. 'only_matching': True,
  69. }, {
  70. 'url': 'http://video.toggle.sg/en/movies/seven-days/321936',
  71. 'only_matching': True,
  72. }, {
  73. 'url': 'https://video.toggle.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
  74. 'only_matching': True,
  75. }, {
  76. 'url': 'http://video.toggle.sg/en/channels/eleven-plus/401585',
  77. 'only_matching': True,
  78. }]
  79. _FORMAT_PREFERENCES = {
  80. 'wvm-STBMain': -10,
  81. 'wvm-iPadMain': -20,
  82. 'wvm-iPhoneMain': -30,
  83. 'wvm-Android': -40,
  84. }
  85. _API_USER = 'tvpapi_147'
  86. _API_PASS = '11111'
  87. def _real_extract(self, url):
  88. video_id = self._match_id(url)
  89. webpage = self._download_webpage(
  90. url, video_id, note='Downloading video page')
  91. api_user = self._search_regex(
  92. r'apiUser\s*:\s*(["\'])(?P<user>.+?)\1', webpage, 'apiUser',
  93. default=self._API_USER, group='user')
  94. api_pass = self._search_regex(
  95. r'apiPass\s*:\s*(["\'])(?P<pass>.+?)\1', webpage, 'apiPass',
  96. default=self._API_PASS, group='pass')
  97. params = {
  98. 'initObj': {
  99. 'Locale': {
  100. 'LocaleLanguage': '',
  101. 'LocaleCountry': '',
  102. 'LocaleDevice': '',
  103. 'LocaleUserState': 0
  104. },
  105. 'Platform': 0,
  106. 'SiteGuid': 0,
  107. 'DomainID': '0',
  108. 'UDID': '',
  109. 'ApiUser': api_user,
  110. 'ApiPass': api_pass
  111. },
  112. 'MediaID': video_id,
  113. 'mediaType': 0,
  114. }
  115. req = sanitized_Request(
  116. 'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
  117. json.dumps(params).encode('utf-8'))
  118. info = self._download_json(req, video_id, 'Downloading video info json')
  119. title = info['MediaName']
  120. formats = []
  121. for video_file in info.get('Files', []):
  122. video_url, vid_format = video_file.get('URL'), video_file.get('Format')
  123. if not video_url or video_url == 'NA' or not vid_format:
  124. continue
  125. ext = determine_ext(video_url)
  126. vid_format = vid_format.replace(' ', '')
  127. # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
  128. if ext == 'm3u8':
  129. formats.extend(self._extract_m3u8_formats(
  130. video_url, video_id, ext='mp4', m3u8_id=vid_format,
  131. note='Downloading %s m3u8 information' % vid_format,
  132. errnote='Failed to download %s m3u8 information' % vid_format,
  133. fatal=False))
  134. elif ext == 'mpd':
  135. formats.extend(self._extract_mpd_formats(
  136. video_url, video_id, mpd_id=vid_format,
  137. note='Downloading %s MPD manifest' % vid_format,
  138. errnote='Failed to download %s MPD manifest' % vid_format,
  139. fatal=False))
  140. elif ext == 'ism':
  141. formats.extend(self._extract_ism_formats(
  142. video_url, video_id, ism_id=vid_format,
  143. note='Downloading %s ISM manifest' % vid_format,
  144. errnote='Failed to download %s ISM manifest' % vid_format,
  145. fatal=False))
  146. elif ext in ('mp4', 'wvm'):
  147. # wvm are drm-protected files
  148. formats.append({
  149. 'ext': ext,
  150. 'url': video_url,
  151. 'format_id': vid_format,
  152. 'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1,
  153. 'format_note': 'DRM-protected video' if ext == 'wvm' else None
  154. })
  155. if not formats:
  156. # Most likely because geo-blocked
  157. raise ExtractorError('No downloadable videos found', expected=True)
  158. self._sort_formats(formats)
  159. duration = int_or_none(info.get('Duration'))
  160. description = info.get('Description')
  161. created_at = parse_iso8601(info.get('CreationDate') or None)
  162. average_rating = float_or_none(info.get('Rating'))
  163. view_count = int_or_none(info.get('ViewCounter') or info.get('view_counter'))
  164. like_count = int_or_none(info.get('LikeCounter') or info.get('like_counter'))
  165. thumbnails = []
  166. for picture in info.get('Pictures', []):
  167. if not isinstance(picture, dict):
  168. continue
  169. pic_url = picture.get('URL')
  170. if not pic_url:
  171. continue
  172. thumbnail = {
  173. 'url': pic_url,
  174. }
  175. pic_size = picture.get('PicSize', '')
  176. m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
  177. if m:
  178. thumbnail.update({
  179. 'width': int(m.group('width')),
  180. 'height': int(m.group('height')),
  181. })
  182. thumbnails.append(thumbnail)
  183. return {
  184. 'id': video_id,
  185. 'title': title,
  186. 'description': description,
  187. 'duration': duration,
  188. 'timestamp': created_at,
  189. 'average_rating': average_rating,
  190. 'view_count': view_count,
  191. 'like_count': like_count,
  192. 'thumbnails': thumbnails,
  193. 'formats': formats,
  194. }