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.

238 lines
9.0 KiB

10 years ago
10 years ago
10 years ago
10 years ago
10 years ago
10 years ago
10 years ago
10 years ago
10 years ago
10 years ago
10 years ago
  1. from __future__ import unicode_literals
  2. import re
  3. import json
  4. import os
  5. from .common import InfoExtractor
  6. from ..compat import (
  7. compat_urlparse,
  8. compat_urllib_parse,
  9. compat_urllib_parse_urlparse
  10. )
  11. from ..utils import (
  12. unified_strdate,
  13. )
  14. class NHLBaseInfoExtractor(InfoExtractor):
  15. @staticmethod
  16. def _fix_json(json_string):
  17. return json_string.replace('\\\'', '\'')
  18. def _real_extract_video(self, video_id):
  19. vid_parts = video_id.split(',')
  20. if len(vid_parts) == 3:
  21. video_id = '%s0%s%s-X-h' % (vid_parts[0][:4], vid_parts[1], vid_parts[2].rjust(4, '0'))
  22. json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
  23. data = self._download_json(
  24. json_url, video_id, transform_source=self._fix_json)
  25. return self._extract_video(data[0])
  26. def _extract_video(self, info):
  27. video_id = info['id']
  28. self.report_extraction(video_id)
  29. initial_video_url = info['publishPoint']
  30. if info['formats'] == '1':
  31. parsed_url = compat_urllib_parse_urlparse(initial_video_url)
  32. filename, ext = os.path.splitext(parsed_url.path)
  33. path = '%s_sd%s' % (filename, ext)
  34. data = compat_urllib_parse.urlencode({
  35. 'type': 'fvod',
  36. 'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:])
  37. })
  38. path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
  39. path_doc = self._download_xml(
  40. path_url, video_id, 'Downloading final video url')
  41. video_url = path_doc.find('path').text
  42. else:
  43. video_url = initial_video_url
  44. join = compat_urlparse.urljoin
  45. ret = {
  46. 'id': video_id,
  47. 'title': info['name'],
  48. 'url': video_url,
  49. 'description': info['description'],
  50. 'duration': int(info['duration']),
  51. 'thumbnail': join(join(video_url, '/u/'), info['bigImage']),
  52. 'upload_date': unified_strdate(info['releaseDate'].split('.')[0]),
  53. }
  54. if video_url.startswith('rtmp:'):
  55. mobj = re.match(r'(?P<tc_url>rtmp://[^/]+/(?P<app>[a-z0-9/]+))/(?P<play_path>mp4:.*)', video_url)
  56. ret.update({
  57. 'tc_url': mobj.group('tc_url'),
  58. 'play_path': mobj.group('play_path'),
  59. 'app': mobj.group('app'),
  60. 'no_resume': True,
  61. })
  62. return ret
  63. class NHLIE(NHLBaseInfoExtractor):
  64. IE_NAME = 'nhl.com'
  65. _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/(?:console|embed)?(?:\?(?:.*?[?&])?)(?:id|hlg|playlist)=(?P<id>[-0-9a-zA-Z,]+)'
  66. _TESTS = [{
  67. 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
  68. 'md5': 'db704a4ea09e8d3988c85e36cc892d09',
  69. 'info_dict': {
  70. 'id': '453614',
  71. 'ext': 'mp4',
  72. 'title': 'Quick clip: Weise 4-3 goal vs Flames',
  73. 'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.',
  74. 'duration': 18,
  75. 'upload_date': '20131006',
  76. },
  77. }, {
  78. 'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h',
  79. 'md5': 'd22e82bc592f52d37d24b03531ee9696',
  80. 'info_dict': {
  81. 'id': '2014020024-628-h',
  82. 'ext': 'mp4',
  83. 'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)',
  84. 'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014',
  85. 'duration': 0,
  86. 'upload_date': '20141011',
  87. },
  88. }, {
  89. 'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802',
  90. 'md5': 'c78fc64ea01777e426cfc202b746c825',
  91. 'info_dict': {
  92. 'id': '58665',
  93. 'ext': 'flv',
  94. 'title': 'Classic Game In Six - April 22, 1979',
  95. 'description': 'It was the last playoff game for the Leafs in the decade, and the last time the Leafs and Habs played in the playoffs. Great game, not a great ending.',
  96. 'duration': 400,
  97. 'upload_date': '20100129'
  98. },
  99. }, {
  100. 'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
  101. 'only_matching': True,
  102. }, {
  103. 'url': 'http://video.nhl.com/videocenter/?id=736722',
  104. 'only_matching': True,
  105. }, {
  106. 'url': 'http://video.nhl.com/videocenter/console?hlg=20142015,2,299&lang=en',
  107. 'md5': '076fcb88c255154aacbf0a7accc3f340',
  108. 'info_dict': {
  109. 'id': '2014020299-X-h',
  110. 'ext': 'mp4',
  111. 'title': 'Penguins at Islanders / Game Highlights',
  112. 'description': 'Home broadcast - Pittsburgh Penguins at New York Islanders - November 22, 2014',
  113. 'duration': 268,
  114. 'upload_date': '20141122',
  115. }
  116. }, {
  117. 'url': 'http://video.oilers.nhl.com/videocenter/console?id=691469&catid=4',
  118. 'info_dict': {
  119. 'id': '691469',
  120. 'ext': 'mp4',
  121. 'title': 'RAW | Craig MacTavish Full Press Conference',
  122. 'description': 'Oilers GM Craig MacTavish addresses the media at Rexall Place on Friday.',
  123. 'upload_date': '20141205',
  124. },
  125. 'params': {
  126. 'skip_download': True, # Requires rtmpdump
  127. }
  128. }, {
  129. 'url': 'http://video.nhl.com/videocenter/embed?playlist=836127',
  130. 'only_matching': True,
  131. }]
  132. def _real_extract(self, url):
  133. video_id = self._match_id(url)
  134. return self._real_extract_video(video_id)
  135. class NHLNewsIE(NHLBaseInfoExtractor):
  136. IE_NAME = 'nhl.com:news'
  137. IE_DESC = 'NHL news'
  138. _VALID_URL = r'https?://(?:.+?\.)?nhl\.com/(?:ice|club)/news\.html?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
  139. _TESTS = [{
  140. 'url': 'http://www.nhl.com/ice/news.htm?id=750727',
  141. 'md5': '4b3d1262e177687a3009937bd9ec0be8',
  142. 'info_dict': {
  143. 'id': '736722',
  144. 'ext': 'mp4',
  145. 'title': 'Cal Clutterbuck has been fined $2,000',
  146. 'description': 'md5:45fe547d30edab88b23e0dd0ab1ed9e6',
  147. 'duration': 37,
  148. 'upload_date': '20150128',
  149. },
  150. }, {
  151. # iframe embed
  152. 'url': 'http://sabres.nhl.com/club/news.htm?id=780189',
  153. 'md5': '9f663d1c006c90ac9fb82777d4294e12',
  154. 'info_dict': {
  155. 'id': '836127',
  156. 'ext': 'mp4',
  157. 'title': 'Morning Skate: OTT vs. BUF (9/23/15)',
  158. 'description': "Brian Duff chats with Tyler Ennis prior to Buffalo's first preseason home game.",
  159. 'duration': 93,
  160. 'upload_date': '20150923',
  161. },
  162. }]
  163. def _real_extract(self, url):
  164. news_id = self._match_id(url)
  165. webpage = self._download_webpage(url, news_id)
  166. video_id = self._search_regex(
  167. [r'pVid(\d+)', r"nlid\s*:\s*'(\d+)'",
  168. r'<iframe[^>]+src=["\']https?://video.*?\.nhl\.com/videocenter/embed\?.*\bplaylist=(\d+)'],
  169. webpage, 'video id')
  170. return self._real_extract_video(video_id)
  171. class NHLVideocenterIE(NHLBaseInfoExtractor):
  172. IE_NAME = 'nhl.com:videocenter'
  173. IE_DESC = 'NHL videocenter category'
  174. _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
  175. _TEST = {
  176. 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
  177. 'info_dict': {
  178. 'id': '999',
  179. 'title': 'Highlights',
  180. },
  181. 'playlist_count': 12,
  182. }
  183. def _real_extract(self, url):
  184. mobj = re.match(self._VALID_URL, url)
  185. team = mobj.group('team')
  186. webpage = self._download_webpage(url, team)
  187. cat_id = self._search_regex(
  188. [r'var defaultCatId = "(.+?)";',
  189. r'{statusIndex:0,index:0,.*?id:(.*?),'],
  190. webpage, 'category id')
  191. playlist_title = self._html_search_regex(
  192. r'tab0"[^>]*?>(.*?)</td>',
  193. webpage, 'playlist title', flags=re.DOTALL).lower().capitalize()
  194. data = compat_urllib_parse.urlencode({
  195. 'cid': cat_id,
  196. # This is the default value
  197. 'count': 12,
  198. 'ptrs': 3,
  199. 'format': 'json',
  200. })
  201. path = '/videocenter/servlets/browse?' + data
  202. request_url = compat_urlparse.urljoin(url, path)
  203. response = self._download_webpage(request_url, playlist_title)
  204. response = self._fix_json(response)
  205. if not response.strip():
  206. self._downloader.report_warning('Got an empty response, trying '
  207. 'adding the "newvideos" parameter')
  208. response = self._download_webpage(request_url + '&newvideos=true',
  209. playlist_title)
  210. response = self._fix_json(response)
  211. videos = json.loads(response)
  212. return {
  213. '_type': 'playlist',
  214. 'title': playlist_title,
  215. 'id': cat_id,
  216. 'entries': [self._extract_video(v) for v in videos],
  217. }