[tube8] Fix extraction and extract all formats (Closes #8281)
This commit is contained in:
		| @@ -1,10 +1,9 @@ | |||||||
| from __future__ import unicode_literals | from __future__ import unicode_literals | ||||||
|  |  | ||||||
| import json |  | ||||||
| import re | import re | ||||||
|  |  | ||||||
| from .common import InfoExtractor | from .common import InfoExtractor | ||||||
| from ..compat import compat_urllib_parse_urlparse | from ..compat import compat_str | ||||||
| from ..utils import ( | from ..utils import ( | ||||||
|     int_or_none, |     int_or_none, | ||||||
|     sanitized_Request, |     sanitized_Request, | ||||||
| @@ -44,14 +43,28 @@ class Tube8IE(InfoExtractor): | |||||||
|         req.add_header('Cookie', 'age_verified=1') |         req.add_header('Cookie', 'age_verified=1') | ||||||
|         webpage = self._download_webpage(req, display_id) |         webpage = self._download_webpage(req, display_id) | ||||||
|  |  | ||||||
|         flashvars = json.loads(self._html_search_regex( |         flashvars = self._parse_json( | ||||||
|             r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars')) |             self._search_regex( | ||||||
|  |                 r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'), | ||||||
|  |             video_id) | ||||||
|  |  | ||||||
|         video_url = flashvars['video_url'] |         formats = [] | ||||||
|  |         for key, video_url in flashvars.items(): | ||||||
|  |             if not isinstance(video_url, compat_str) or not video_url.startswith('http'): | ||||||
|  |                 continue | ||||||
|  |             height = self._search_regex( | ||||||
|  |                 r'quality_(\d+)[pP]', key, 'height', default=None) | ||||||
|  |             if not height: | ||||||
|  |                 continue | ||||||
|             if flashvars.get('encrypted') is True: |             if flashvars.get('encrypted') is True: | ||||||
|             video_url = aes_decrypt_text(video_url, flashvars['video_title'], 32).decode('utf-8') |                 video_url = aes_decrypt_text( | ||||||
|         path = compat_urllib_parse_urlparse(video_url).path |                     video_url, flashvars['video_title'], 32).decode('utf-8') | ||||||
|         format_id = '-'.join(path.split('/')[4].split('_')[:2]) |             formats.append({ | ||||||
|  |                 'url': video_url, | ||||||
|  |                 'format_id': '%sp' % height, | ||||||
|  |                 'height': int(height), | ||||||
|  |             }) | ||||||
|  |         self._sort_formats(formats) | ||||||
|  |  | ||||||
|         thumbnail = flashvars.get('image_url') |         thumbnail = flashvars.get('image_url') | ||||||
|  |  | ||||||
| @@ -79,15 +92,14 @@ class Tube8IE(InfoExtractor): | |||||||
|         return { |         return { | ||||||
|             'id': video_id, |             'id': video_id, | ||||||
|             'display_id': display_id, |             'display_id': display_id, | ||||||
|             'url': video_url, |  | ||||||
|             'title': title, |             'title': title, | ||||||
|             'description': description, |             'description': description, | ||||||
|             'thumbnail': thumbnail, |             'thumbnail': thumbnail, | ||||||
|             'uploader': uploader, |             'uploader': uploader, | ||||||
|             'format_id': format_id, |  | ||||||
|             'view_count': view_count, |             'view_count': view_count, | ||||||
|             'like_count': like_count, |             'like_count': like_count, | ||||||
|             'dislike_count': dislike_count, |             'dislike_count': dislike_count, | ||||||
|             'comment_count': comment_count, |             'comment_count': comment_count, | ||||||
|             'age_limit': 18, |             'age_limit': 18, | ||||||
|  |             'formats': formats, | ||||||
|         } |         } | ||||||
|   | |||||||
		Reference in New Issue
	
	Block a user
	 Sergey M․
					Sergey M․