ytdl-nightly/youtube_dl/extractor/addanime.py

95 lines
3.2 KiB
Python
Raw Normal View History

2014-03-24 16:39:53 +01:00
from __future__ import unicode_literals
2013-08-28 10:28:16 +02:00
import re
from .common import InfoExtractor
from ..compat import (
2013-08-28 10:28:16 +02:00
compat_HTTPError,
compat_str,
compat_urllib_parse,
compat_urllib_parse_urlparse,
)
from ..utils import (
2013-08-28 10:28:16 +02:00
ExtractorError,
qualities,
2013-08-28 10:28:16 +02:00
)
class AddAnimeIE(InfoExtractor):
_VALID_URL = r'http://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
2015-04-07 17:01:35 +02:00
_TESTS = [{
2014-03-24 16:39:53 +01:00
'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
'md5': '72954ea10bc979ab5e2eb288b21425a0',
'info_dict': {
'id': '24MR3YO5SAS9',
'ext': 'mp4',
'description': 'One Piece 606',
'title': 'One Piece 606',
2013-08-28 10:28:16 +02:00
}
2015-04-07 17:01:35 +02:00
}, {
'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
'only_matching': True,
}]
2013-08-28 10:28:16 +02:00
def _real_extract(self, url):
2014-11-26 12:40:05 +01:00
video_id = self._match_id(url)
2013-08-28 10:28:16 +02:00
try:
webpage = self._download_webpage(url, video_id)
except ExtractorError as ee:
2013-10-28 11:24:47 +01:00
if not isinstance(ee.cause, compat_HTTPError) or \
ee.cause.code != 503:
2013-08-28 10:28:16 +02:00
raise
redir_webpage = ee.cause.read().decode('utf-8')
action = self._search_regex(
r'<form id="challenge-form" action="([^"]+)"',
2014-03-24 16:39:53 +01:00
redir_webpage, 'Redirect form')
2013-08-28 10:28:16 +02:00
vc = self._search_regex(
r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
2014-03-24 16:39:53 +01:00
redir_webpage, 'redirect vc value')
2013-08-28 10:28:16 +02:00
av = re.search(
r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
redir_webpage)
if av is None:
2014-11-26 12:40:05 +01:00
raise ExtractorError('Cannot find redirect math task')
2013-08-28 10:28:16 +02:00
av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
parsed_url = compat_urllib_parse_urlparse(url)
av_val = av_res + len(parsed_url.netloc)
confirm_url = (
2014-03-24 16:39:53 +01:00
parsed_url.scheme + '://' + parsed_url.netloc +
2013-08-28 10:28:16 +02:00
action + '?' +
compat_urllib_parse.urlencode({
'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
self._download_webpage(
confirm_url, video_id,
2014-03-24 16:39:53 +01:00
note='Confirming after redirect')
2013-08-28 10:28:16 +02:00
webpage = self._download_webpage(url, video_id)
FORMATS = ('normal', 'hq')
quality = qualities(FORMATS)
2013-10-28 11:24:47 +01:00
formats = []
for format_id in FORMATS:
2013-10-28 11:24:47 +01:00
rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
2014-03-24 16:39:53 +01:00
video_url = self._search_regex(rex, webpage, 'video file URLx',
2013-10-28 11:24:47 +01:00
fatal=False)
if not video_url:
continue
formats.append({
'format_id': format_id,
'url': video_url,
'quality': quality(format_id),
2013-10-28 11:24:47 +01:00
})
2014-03-24 16:39:53 +01:00
self._sort_formats(formats)
2013-08-28 10:28:16 +02:00
video_title = self._og_search_title(webpage)
video_description = self._og_search_description(webpage)
return {
'_type': 'video',
2014-03-24 16:39:53 +01:00
'id': video_id,
2013-10-28 11:24:47 +01:00
'formats': formats,
2013-08-28 10:28:16 +02:00
'title': video_title,
'description': video_description
}