youtube-dl/youtube_dl/extractor/shared.py

142 lines
4.3 KiB
Python
Raw Normal View History

2014-07-24 14:12:45 +00:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote_plus,
)
2014-07-24 14:12:45 +00:00
from ..utils import (
determine_ext,
2014-07-24 14:12:45 +00:00
ExtractorError,
int_or_none,
js_to_json,
KNOWN_EXTENSIONS,
parse_filesize,
rot47,
2018-11-10 16:37:27 +00:00
url_or_none,
urlencode_postdata,
2014-07-24 14:12:45 +00:00
)
2016-10-23 11:07:56 +00:00
class SharedBaseIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, video_id)
if self._FILE_NOT_FOUND in webpage:
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
video_url = self._extract_video_url(webpage, video_id, url)
2019-02-13 15:29:43 +00:00
title = self._extract_title(webpage)
filesize = int_or_none(self._extract_filesize(webpage))
2016-10-23 11:07:56 +00:00
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'filesize': filesize,
'title': title,
}
2019-02-13 15:29:43 +00:00
def _extract_title(self, webpage):
return compat_b64decode(self._html_search_meta(
'full:title', webpage, 'title')).decode('utf-8')
def _extract_filesize(self, webpage):
return self._html_search_meta(
'full:size', webpage, 'file size', fatal=False)
2016-10-23 11:07:56 +00:00
class SharedIE(SharedBaseIE):
IE_DESC = 'shared.sx'
_VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})'
_FILE_NOT_FOUND = '>File does not exist<'
2014-07-24 14:12:45 +00:00
2016-10-23 11:07:56 +00:00
_TEST = {
2014-07-24 14:12:45 +00:00
'url': 'http://shared.sx/0060718775',
2014-08-13 11:24:46 +00:00
'md5': '106fefed92a8a2adb8c98e6a0652f49b',
2014-07-24 14:12:45 +00:00
'info_dict': {
'id': '0060718775',
'ext': 'mp4',
2014-08-13 11:24:46 +00:00
'title': 'Bmp4',
2015-08-26 16:06:10 +00:00
'filesize': 1720110,
2014-07-24 14:12:45 +00:00
},
2016-10-23 11:07:56 +00:00
}
2014-07-24 14:12:45 +00:00
2016-10-23 11:07:56 +00:00
def _extract_video_url(self, webpage, video_id, url):
download_form = self._hidden_inputs(webpage)
video_page = self._download_webpage(
2016-10-23 11:07:56 +00:00
url, video_id, 'Downloading video page',
data=urlencode_postdata(download_form),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
2016-10-23 11:07:56 +00:00
'Referer': url,
})
2014-07-24 14:12:45 +00:00
video_url = self._html_search_regex(
r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
video_page, 'video URL', group='url')
2014-07-24 14:12:45 +00:00
2016-10-23 11:07:56 +00:00
return video_url
class VivoIE(SharedBaseIE):
IE_DESC = 'vivo.sx'
_VALID_URL = r'https?://vivo\.s[xt]/(?P<id>[\da-z]{10})'
2016-10-23 11:07:56 +00:00
_FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
_TESTS = [{
2016-10-23 11:07:56 +00:00
'url': 'http://vivo.sx/d7ddda0e78',
'md5': '15b3af41be0b4fe01f4df075c2678b2c',
'info_dict': {
'id': 'd7ddda0e78',
2014-07-24 14:12:45 +00:00
'ext': 'mp4',
2016-10-23 11:07:56 +00:00
'title': 'Chicken',
'filesize': 515659,
2016-10-23 11:07:56 +00:00
},
}, {
'url': 'http://vivo.st/d7ddda0e78',
'only_matching': True,
}]
2016-10-23 11:07:56 +00:00
2019-02-13 15:29:43 +00:00
def _extract_title(self, webpage):
title = self._html_search_regex(
2019-02-13 15:29:43 +00:00
r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage,
'title', default=None, group='title')
if title:
ext = determine_ext(title)
if ext.lower() in KNOWN_EXTENSIONS:
title = title.rpartition('.' + ext)[0]
return title
2019-02-13 15:29:43 +00:00
return self._og_search_title(webpage)
def _extract_filesize(self, webpage):
return parse_filesize(self._search_regex(
r'data-type=["\']video["\'][^>]*>Watch.*?<strong>\s*\((.+?)\)',
webpage, 'filesize', fatal=False))
def _extract_video_url(self, webpage, video_id, url):
def decode_url_old(encoded_url):
2018-11-10 16:37:27 +00:00
return compat_b64decode(encoded_url).decode('utf-8')
stream_url = self._search_regex(
2018-11-10 16:37:27 +00:00
r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'stream url', default=None, group='url')
if stream_url:
stream_url = url_or_none(decode_url_old(stream_url))
2018-11-10 16:37:27 +00:00
if stream_url:
return stream_url
def decode_url(encoded_url):
return rot47(compat_urllib_parse_unquote_plus(encoded_url))
return decode_url(self._parse_json(
2016-10-23 11:07:56 +00:00
self._search_regex(
r'(?s)InitializeStream\s*\(\s*({.+?})\s*\)\s*;', webpage,
'stream'),
video_id, transform_source=js_to_json)['source'])