mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-10-14 06:18:30 +00:00
[ie/xhamster] Fix extractor (#14345)
Fix a1c98226a4
Closes #14145
Authored by: arand, thegymguy
Co-authored-by: arand <183498+arand@users.noreply.github.com>
This commit is contained in:
parent
b81e9272dc
commit
677997d84e
@ -1,4 +1,5 @@
|
|||||||
import base64
|
import base64
|
||||||
|
import codecs
|
||||||
import itertools
|
import itertools
|
||||||
import re
|
import re
|
||||||
|
|
||||||
@ -11,13 +12,13 @@
|
|||||||
extract_attributes,
|
extract_attributes,
|
||||||
float_or_none,
|
float_or_none,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
|
join_nonempty,
|
||||||
parse_duration,
|
parse_duration,
|
||||||
str_or_none,
|
str_or_none,
|
||||||
try_call,
|
try_call,
|
||||||
try_get,
|
try_get,
|
||||||
unified_strdate,
|
unified_strdate,
|
||||||
url_or_none,
|
url_or_none,
|
||||||
urljoin,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@ -142,6 +143,27 @@ class XHamsterIE(InfoExtractor):
|
|||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
|
_XOR_KEY = b'xh7999'
|
||||||
|
|
||||||
|
def _decipher_format_url(self, format_url, format_id):
|
||||||
|
cipher_type, _, ciphertext = try_call(
|
||||||
|
lambda: base64.b64decode(format_url).decode().partition('_')) or [None] * 3
|
||||||
|
|
||||||
|
if not cipher_type or not ciphertext:
|
||||||
|
self.report_warning(f'Skipping format "{format_id}": failed to decipher URL')
|
||||||
|
return None
|
||||||
|
|
||||||
|
if cipher_type == 'xor':
|
||||||
|
return bytes(
|
||||||
|
a ^ b for a, b in
|
||||||
|
zip(ciphertext.encode(), itertools.cycle(self._XOR_KEY))).decode()
|
||||||
|
|
||||||
|
if cipher_type == 'rot13':
|
||||||
|
return codecs.decode(ciphertext, cipher_type)
|
||||||
|
|
||||||
|
self.report_warning(f'Skipping format "{format_id}": unsupported cipher type "{cipher_type}"')
|
||||||
|
return None
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = self._match_valid_url(url)
|
mobj = self._match_valid_url(url)
|
||||||
video_id = mobj.group('id') or mobj.group('id_2')
|
video_id = mobj.group('id') or mobj.group('id_2')
|
||||||
@ -212,7 +234,7 @@ def get_height(s):
|
|||||||
hls_url = hls_sources.get(hls_format_key)
|
hls_url = hls_sources.get(hls_format_key)
|
||||||
if not hls_url:
|
if not hls_url:
|
||||||
continue
|
continue
|
||||||
hls_url = urljoin(url, hls_url)
|
hls_url = self._decipher_format_url(hls_url, f'hls-{hls_format_key}')
|
||||||
if not hls_url or hls_url in format_urls:
|
if not hls_url or hls_url in format_urls:
|
||||||
continue
|
continue
|
||||||
format_urls.add(hls_url)
|
format_urls.add(hls_url)
|
||||||
@ -221,7 +243,7 @@ def get_height(s):
|
|||||||
m3u8_id='hls', fatal=False))
|
m3u8_id='hls', fatal=False))
|
||||||
standard_sources = xplayer_sources.get('standard')
|
standard_sources = xplayer_sources.get('standard')
|
||||||
if isinstance(standard_sources, dict):
|
if isinstance(standard_sources, dict):
|
||||||
for format_id, formats_list in standard_sources.items():
|
for identifier, formats_list in standard_sources.items():
|
||||||
if not isinstance(formats_list, list):
|
if not isinstance(formats_list, list):
|
||||||
continue
|
continue
|
||||||
for standard_format in formats_list:
|
for standard_format in formats_list:
|
||||||
@ -231,12 +253,11 @@ def get_height(s):
|
|||||||
standard_url = standard_format.get(standard_format_key)
|
standard_url = standard_format.get(standard_format_key)
|
||||||
if not standard_url:
|
if not standard_url:
|
||||||
continue
|
continue
|
||||||
decoded = try_call(lambda: base64.b64decode(standard_url))
|
quality = (str_or_none(standard_format.get('quality'))
|
||||||
if decoded and decoded[:4] == b'xor_':
|
or str_or_none(standard_format.get('label'))
|
||||||
standard_url = bytes(
|
or '')
|
||||||
a ^ b for a, b in
|
format_id = join_nonempty(identifier, quality)
|
||||||
zip(decoded[4:], itertools.cycle(b'xh7999'))).decode()
|
standard_url = self._decipher_format_url(standard_url, format_id)
|
||||||
standard_url = urljoin(url, standard_url)
|
|
||||||
if not standard_url or standard_url in format_urls:
|
if not standard_url or standard_url in format_urls:
|
||||||
continue
|
continue
|
||||||
format_urls.add(standard_url)
|
format_urls.add(standard_url)
|
||||||
@ -246,11 +267,9 @@ def get_height(s):
|
|||||||
standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||||
m3u8_id='hls', fatal=False))
|
m3u8_id='hls', fatal=False))
|
||||||
continue
|
continue
|
||||||
quality = (str_or_none(standard_format.get('quality'))
|
|
||||||
or str_or_none(standard_format.get('label'))
|
|
||||||
or '')
|
|
||||||
formats.append({
|
formats.append({
|
||||||
'format_id': f'{format_id}-{quality}',
|
'format_id': format_id,
|
||||||
'url': standard_url,
|
'url': standard_url,
|
||||||
'ext': ext,
|
'ext': ext,
|
||||||
'height': get_height(quality),
|
'height': get_height(quality),
|
||||||
|
Loading…
Reference in New Issue
Block a user