depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-05-19 19:49:33 +00:00
Code Issues Releases Wiki Activity

[doodstream] only use metadata from the page

Browse source
This commit is contained in:
schnusch 2021-08-13 13:29:07 +02:00
parent 3be8521c91
commit 948c020489
1 changed files with 8 additions and 39 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

47
youtube_dl/extractor/doodstream.py
View file

@ -9,36 +9,9 @@ from .common import InfoExtractor
from ..utils import ( from ..utils import (
js_to_json, js_to_json,
urljoin, urljoin,
try_get,
) )
def doodExe(crp, crs):
if crp == 'N_crp':
return crs
sorted_crp = ''.join(sorted(crp))
result = ''
for c in crs:
i = crp.find(c)
if i >= 0:
result += sorted_crp[i]
result = result.replace('+.+', '(')
result = result.replace('+..+', ')')
result = result.replace('+-+', '[')
result = result.replace('+--+', ']')
result = result.replace('+', ' ')
return result
def try_doodExe(metadata, key):
try:
x = metadata[key]
# everything that can go wrong in this call raises a TypeError
return doodExe(**x)
except (KeyError, TypeError):
return None
class DoodStreamIE(InfoExtractor): class DoodStreamIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:doodstream\.com|dood\.(?:la|so|to|watch))/[de]/(?P<id>[^/?#]+)' _VALID_URL = r'https?://(?:www\.)?(?:doodstream\.com|dood\.(?:la|so|to|watch))/[de]/(?P<id>[^/?#]+)'
_TESTS = [{ _TESTS = [{
@ -49,8 +22,6 @@ class DoodStreamIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Big Buck Bunny Trailer', 'title': 'Big Buck Bunny Trailer',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'filesize': 4447915,
'duration': 33,
}, },
}] }]
@ -61,12 +32,12 @@ class DoodStreamIE(InfoExtractor):
referer = {'Referer': url} referer = {'Referer': url}
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
metadata_url = self._html_search_regex(r"('/cptr/[^']*')", webpage, title = self._html_search_regex(r'<title>(.+?)\s+-\s+DoodStream</title>',
'video metadata') webpage, 'title')
metadata_url = self._parse_json(metadata_url, video_id, thumbnail = self._html_search_regex(r"('https?://img\.doodcdn\.com/splash/.+?')",
transform_source=js_to_json) webpage, 'thumbnail')
metadata_url = urljoin(url, metadata_url) thumbnail = self._parse_json(thumbnail, video_id,
metadata = self._download_json(metadata_url, video_id, headers=referer) transform_source=js_to_json)
token = self._html_search_regex(r"[?&]token=([a-z0-9]+)[&']", webpage, 'token') token = self._html_search_regex(r"[?&]token=([a-z0-9]+)[&']", webpage, 'token')
auth_url = self._html_search_regex(r"('/pass_md5.*?')", webpage, auth_url = self._html_search_regex(r"('/pass_md5.*?')", webpage,
@ -80,11 +51,9 @@ class DoodStreamIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'title': try_doodExe(metadata, 'ttl') or video_id, 'title': title,
'url': final_url, 'url': final_url,
'http_headers': referer, 'http_headers': referer,
'ext': 'mp4', 'ext': 'mp4',
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': thumbnail,
'filesize': try_get(try_doodExe(metadata, 'siz'), lambda x: int(x, 10)),
'duration': try_get(try_doodExe(metadata, 'len'), lambda x: int(x, 10)),
} }