diff options
author | Yen Chi Hsuan <yan12125@gmail.com> | 2015-11-11 23:17:59 +0800 |
---|---|---|
committer | Yen Chi Hsuan <yan12125@gmail.com> | 2015-11-11 23:17:59 +0800 |
commit | 8b8a39e279b02926197230024e64a50d7995b95d (patch) | |
tree | 960893ca3423ef95a43def29228fb2bd961ee8c6 | |
parent | 990e6e8fa346224967f123a50146377088acbd75 (diff) |
[vidto] Several simplifications and improvements
1. Use InfoExtractor._hidden_inputs
2. Fetch title from <title> tag
3. Cookies are preserved automatically
4. Use single quotes everywhere
5. Do not declare variables for one-time use only
-rw-r--r-- | youtube_dl/extractor/vidto.py | 51 |
1 files changed, 18 insertions, 33 deletions
diff --git a/youtube_dl/extractor/vidto.py b/youtube_dl/extractor/vidto.py index 45b21e2a9..5ebf0f3d3 100644 --- a/youtube_dl/extractor/vidto.py +++ b/youtube_dl/extractor/vidto.py @@ -4,24 +4,24 @@ from __future__ import unicode_literals import time from .common import InfoExtractor -from ..utils import encode_dict -from ..compat import ( - compat_urllib_request, - compat_urllib_parse +from ..utils import ( + encode_dict, + remove_end, + urlencode_postdata, ) +from ..compat import compat_urllib_request class VidtoIE(InfoExtractor): IE_NAME = 'vidto' IE_DESC = 'VidTo.me' _VALID_URL = r'https?://(?:www\.)?vidto\.me/(?P<id>[0-9a-zA-Z]+)\.html' - _HOST = 'vidto.me' _TEST = { 'url': 'http://vidto.me/ku5glz52nqe1.html', 'info_dict': { 'id': 'ku5glz52nqe1', 'ext': 'mp4', - 'title': 'test.mp4' + 'title': 'test' } } @@ -29,41 +29,26 @@ class VidtoIE(InfoExtractor): video_id = self._match_id(url) page = self._download_webpage( - 'http://%s/%s.html' % (self._HOST, video_id), video_id, 'Downloading video page') - hash_regex = r'<input type="hidden" name="hash" value="(.*)">' - hash_value = self._search_regex(hash_regex, page, 'hash', fatal=True) - title_regex = r'<input type="hidden" name="fname" value="(.*)">' - title = self._search_regex(title_regex, page, 'title', fatal=False) - id_regex = r'<input type="hidden" name="id" value="(.*)">' - id_value = self._search_regex(id_regex, page, 'id', fatal=True) - cookies = self._get_cookies('http://%s/%s.html' % (self._HOST, video_id)) + 'http://vidto.me/%s.html' % video_id, video_id, 'Downloading video page') - form_str = { - 'op': 'download1', - 'imhuman': 'Proceed to video', - 'usr_login': '', - 'id': id_value, - 'fname': title, - 'referer': '', - 'hash': hash_value, - } - post_data = compat_urllib_parse.urlencode(encode_dict(form_str)).encode('ascii') - req = compat_urllib_request.Request(url, post_data) - req.add_header('Content-type', 'application/x-www-form-urlencoded') - cookie_string = "" - for key in cookies.keys(): - cookie_string += "%s=%s;" % (key, cookies[key].value) + title = remove_end(self._html_search_regex( + r'<Title>\s*([^<]+)\s*</Title>', page, 'title'), ' - Vidto') - req.add_header('Cookie', '%s' % cookie_string) + hidden_fields = self._hidden_inputs(page) - self.to_screen("Waiting for countdown...") + self.to_screen('Waiting for countdown...') time.sleep(7) + + req = compat_urllib_request.Request( + url, urlencode_postdata(encode_dict(hidden_fields))) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + post_result = self._download_webpage( req, video_id, note='Proceed to video...', errnote='unable to proceed') - file_link_regex = r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)' - file_link = self._search_regex(file_link_regex, post_result, 'file_link') + file_link = self._search_regex( + r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)', post_result, 'file_link') return { 'id': video_id, |