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.

102 lines
3.9 KiB

10 years ago
10 years ago
10 years ago
  1. from __future__ import unicode_literals
  2. import re
  3. from .common import InfoExtractor
  4. from ..utils import (
  5. parse_duration,
  6. int_or_none,
  7. xpath_text,
  8. xpath_attr,
  9. )
  10. class NBAIE(InfoExtractor):
  11. _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)?video/(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$'
  12. _TESTS = [{
  13. 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
  14. 'md5': '9e7729d3010a9c71506fd1248f74e4f4',
  15. 'info_dict': {
  16. 'id': '0021200253-okc-bkn-recap',
  17. 'ext': 'flv',
  18. 'title': 'Thunder vs. Nets',
  19. 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
  20. 'duration': 181,
  21. 'timestamp': 1354638466,
  22. 'upload_date': '20121204',
  23. },
  24. }, {
  25. 'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
  26. 'only_matching': True,
  27. }, {
  28. 'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
  29. 'md5': 'b2b39b81cf28615ae0c3360a3f9668c4',
  30. 'info_dict': {
  31. 'id': '0041400301-cle-atl-recap',
  32. 'ext': 'mp4',
  33. 'title': 'Hawks vs. Cavaliers Game 1',
  34. 'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
  35. 'duration': 228,
  36. 'timestamp': 1432134543,
  37. 'upload_date': '20150520',
  38. }
  39. }]
  40. def _real_extract(self, url):
  41. path, video_id = re.match(self._VALID_URL, url).groups()
  42. if path.startswith('nba/'):
  43. path = path[3:]
  44. video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id)
  45. video_id = xpath_text(video_info, 'slug')
  46. title = xpath_text(video_info, 'headline')
  47. description = xpath_text(video_info, 'description')
  48. duration = parse_duration(xpath_text(video_info, 'length'))
  49. timestamp = int_or_none(xpath_attr(video_info, 'dateCreated', 'uts'))
  50. thumbnails = []
  51. for image in video_info.find('images'):
  52. thumbnails.append({
  53. 'id': image.attrib.get('cut'),
  54. 'url': image.text,
  55. 'width': int_or_none(image.attrib.get('width')),
  56. 'height': int_or_none(image.attrib.get('height')),
  57. })
  58. formats = []
  59. for video_file in video_info.findall('.//file'):
  60. video_url = video_file.text
  61. if video_url.startswith('/'):
  62. continue
  63. if video_url.endswith('.m3u8'):
  64. m3u8_formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False)
  65. if m3u8_formats:
  66. formats.extend(m3u8_formats)
  67. elif video_url.endswith('.f4m'):
  68. f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False)
  69. if f4m_formats:
  70. formats.extend(f4m_formats)
  71. else:
  72. key = video_file.attrib.get('bitrate')
  73. format_info = {
  74. 'format_id': key,
  75. 'url': video_url,
  76. }
  77. mobj = re.search(r'(\d+)x(\d+)(?:_(\d+))?', key)
  78. if mobj:
  79. format_info.update({
  80. 'width': int(mobj.group(1)),
  81. 'height': int(mobj.group(2)),
  82. 'tbr': int_or_none(mobj.group(3)),
  83. })
  84. formats.append(format_info)
  85. self._sort_formats(formats)
  86. return {
  87. 'id': video_id,
  88. 'title': title,
  89. 'description': description,
  90. 'duration': duration,
  91. 'timestamp': timestamp,
  92. 'thumbnails': thumbnails,
  93. 'formats': formats,
  94. }