ign.py 4.4 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124
  1. from __future__ import unicode_literals
  2. import re
  3. from .common import InfoExtractor
  4. class IGNIE(InfoExtractor):
  5. """
  6. Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com.
  7. Some videos of it.ign.com are also supported
  8. """
  9. _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles|(?:[^/]*/feature))(/.+)?/(?P<name_or_id>.+)'
  10. IE_NAME = 'ign.com'
  11. _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
  12. _DESCRIPTION_RE = [
  13. r'<span class="page-object-description">(.+?)</span>',
  14. r'id="my_show_video">.*?<p>(.*?)</p>',
  15. ]
  16. _TESTS = [
  17. {
  18. 'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
  19. 'md5': 'eac8bdc1890980122c3b66f14bdd02e9',
  20. 'info_dict': {
  21. 'id': '8f862beef863986b2785559b9e1aa599',
  22. 'ext': 'mp4',
  23. 'title': 'The Last of Us Review',
  24. 'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
  25. }
  26. },
  27. {
  28. 'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
  29. 'playlist': [
  30. {
  31. 'info_dict': {
  32. 'id': '5ebbd138523268b93c9141af17bec937',
  33. 'ext': 'mp4',
  34. 'title': 'GTA 5 Video Review',
  35. 'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
  36. },
  37. },
  38. {
  39. 'info_dict': {
  40. 'id': '638672ee848ae4ff108df2a296418ee2',
  41. 'ext': 'mp4',
  42. 'title': '26 Twisted Moments from GTA 5 in Slow Motion',
  43. 'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
  44. },
  45. },
  46. ],
  47. 'params': {
  48. 'skip_download': True,
  49. },
  50. },
  51. ]
  52. def _find_video_id(self, webpage):
  53. res_id = [
  54. r'data-video-id="(.+?)"',
  55. r'<object id="vid_(.+?)"',
  56. r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
  57. ]
  58. return self._search_regex(res_id, webpage, 'video id')
  59. def _real_extract(self, url):
  60. mobj = re.match(self._VALID_URL, url)
  61. name_or_id = mobj.group('name_or_id')
  62. page_type = mobj.group('type')
  63. webpage = self._download_webpage(url, name_or_id)
  64. if page_type == 'articles':
  65. video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url')
  66. return self.url_result(video_url, ie='IGN')
  67. elif page_type != 'video':
  68. multiple_urls = re.findall(
  69. '<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
  70. webpage)
  71. if multiple_urls:
  72. return [self.url_result(u, ie='IGN') for u in multiple_urls]
  73. video_id = self._find_video_id(webpage)
  74. result = self._get_video_info(video_id)
  75. description = self._html_search_regex(self._DESCRIPTION_RE,
  76. webpage, 'video description', flags=re.DOTALL)
  77. result['description'] = description
  78. return result
  79. def _get_video_info(self, video_id):
  80. config_url = self._CONFIG_URL_TEMPLATE % video_id
  81. config = self._download_json(config_url, video_id)
  82. media = config['playlist']['media']
  83. return {
  84. 'id': media['metadata']['videoId'],
  85. 'url': media['url'],
  86. 'title': media['metadata']['title'],
  87. 'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'),
  88. }
  89. class OneUPIE(IGNIE):
  90. _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)'
  91. IE_NAME = '1up.com'
  92. _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
  93. _TESTS = [{
  94. 'url': 'http://gamevideos.1up.com/video/id/34976',
  95. 'md5': '68a54ce4ebc772e4b71e3123d413163d',
  96. 'info_dict': {
  97. 'id': '34976',
  98. 'ext': 'mp4',
  99. 'title': 'Sniper Elite V2 - Trailer',
  100. 'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf',
  101. }
  102. }]
  103. def _real_extract(self, url):
  104. mobj = re.match(self._VALID_URL, url)
  105. result = super(OneUPIE, self)._real_extract(url)
  106. result['id'] = mobj.group('name_or_id')
  107. return result