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.

106 lines
3.7 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
10 years ago
10 years ago
  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import re
  4. from .common import InfoExtractor
  5. from ..utils import (
  6. unified_strdate,
  7. parse_duration,
  8. int_or_none,
  9. )
  10. class SexyKarmaIE(InfoExtractor):
  11. _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
  12. _TESTS = [{
  13. 'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
  14. 'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
  15. 'info_dict': {
  16. 'id': 'yHI70cOyIHt',
  17. 'display_id': 'taking-a-quick-pee',
  18. 'ext': 'mp4',
  19. 'title': 'Taking a quick pee.',
  20. 'description': '',
  21. 'thumbnail': 're:^https?://.*\.jpg$',
  22. 'uploader': 'wildginger7',
  23. 'upload_date': '20141007',
  24. 'duration': 81,
  25. 'view_count': int,
  26. 'comment_count': int,
  27. 'categories': list,
  28. }
  29. }, {
  30. 'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
  31. 'md5': 'dd216c68d29b49b12842b9babe762a5d',
  32. 'info_dict': {
  33. 'id': '8Id6EZPbuHf',
  34. 'display_id': 'pot-pixie-tribute',
  35. 'ext': 'mp4',
  36. 'title': 'pot_pixie tribute',
  37. 'description': 'tribute',
  38. 'thumbnail': 're:^https?://.*\.jpg$',
  39. 'uploader': 'banffite',
  40. 'upload_date': '20141013',
  41. 'duration': 16,
  42. 'view_count': int,
  43. 'comment_count': int,
  44. 'categories': list,
  45. }
  46. }]
  47. def _real_extract(self, url):
  48. mobj = re.match(self._VALID_URL, url)
  49. video_id = mobj.group('id')
  50. display_id = mobj.group('display_id')
  51. webpage = self._download_webpage(url, display_id)
  52. video_url = self._html_search_regex(
  53. r'<p>Save this video to your computer: </p><p><a href="([^"]+)"',
  54. webpage, 'url')
  55. title = self._html_search_regex(
  56. r'<h2 class="he2"><span>(.*?)</span>',
  57. webpage, 'title')
  58. description = self._html_search_meta(
  59. 'description', webpage, 'description', fatal=False, default='')
  60. thumbnail = self._html_search_regex(
  61. r'<span id="container"><img\s+src="([^"]+)"',
  62. webpage, 'thumbnail', fatal=False)
  63. uploader = self._html_search_regex(
  64. r'class="aupa">\s*(.*?)</a>',
  65. webpage, 'uploader')
  66. upload_date = unified_strdate(self._html_search_regex(
  67. r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False))
  68. duration = parse_duration(self._search_regex(
  69. r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>',
  70. webpage, 'duration', fatal=False))
  71. view_count = int_or_none(self._search_regex(
  72. r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
  73. webpage, 'view count', fatal=False))
  74. comment_count = int_or_none(self._search_regex(
  75. r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
  76. webpage, 'comment count', fatal=False))
  77. categories = self._html_search_meta(
  78. 'keywords', webpage, 'categories',
  79. fatal=False, default='').split(',')
  80. return {
  81. 'id': video_id,
  82. 'display_id': display_id,
  83. 'url': video_url,
  84. 'title': title,
  85. 'description': description,
  86. 'thumbnail': thumbnail,
  87. 'uploader': uploader,
  88. 'upload_date': upload_date,
  89. 'duration': duration,
  90. 'view_count': view_count,
  91. 'comment_count': comment_count,
  92. 'categories': categories,
  93. }