[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
This commit is contained in:
Yen Chi Hsuan 2015-11-11 23:17:59 +08:00
parent 990e6e8fa3
commit 8b8a39e279

View file

@ -4,24 +4,24 @@
import time import time
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import encode_dict from ..utils import (
from ..compat import ( encode_dict,
compat_urllib_request, remove_end,
compat_urllib_parse urlencode_postdata,
) )
from ..compat import compat_urllib_request
class VidtoIE(InfoExtractor): class VidtoIE(InfoExtractor):
IE_NAME = 'vidto' IE_NAME = 'vidto'
IE_DESC = 'VidTo.me' IE_DESC = 'VidTo.me'
_VALID_URL = r'https?://(?:www\.)?vidto\.me/(?P<id>[0-9a-zA-Z]+)\.html' _VALID_URL = r'https?://(?:www\.)?vidto\.me/(?P<id>[0-9a-zA-Z]+)\.html'
_HOST = 'vidto.me'
_TEST = { _TEST = {
'url': 'http://vidto.me/ku5glz52nqe1.html', 'url': 'http://vidto.me/ku5glz52nqe1.html',
'info_dict': { 'info_dict': {
'id': 'ku5glz52nqe1', 'id': 'ku5glz52nqe1',
'ext': 'mp4', 'ext': 'mp4',
'title': 'test.mp4' 'title': 'test'
} }
} }
@ -29,41 +29,26 @@ def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
page = self._download_webpage( page = self._download_webpage(
'http://%s/%s.html' % (self._HOST, video_id), video_id, 'Downloading video page') 'http://vidto.me/%s.html' % 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))
form_str = { title = remove_end(self._html_search_regex(
'op': 'download1', r'<Title>\s*([^<]+)\s*</Title>', page, 'title'), ' - Vidto')
'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)
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) 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( post_result = self._download_webpage(
req, video_id, req, video_id,
note='Proceed to video...', errnote='unable to proceed') 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 = self._search_regex(file_link_regex, post_result, 'file_link') r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)', post_result, 'file_link')
return { return {
'id': video_id, 'id': video_id,