mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-08-15 08:58:28 +00:00
Code Issues Projects Releases Wiki Activity

fix/iqiyi-extractor

Browse Source
This commit is contained in:
yuan 2025-08-07 07:25:56 -07:00
parent e8d2807296
commit 95a2971231
1 changed files with 38 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
yt_dlp/extractor/iqiyi.py
View File

@ -1,3 +1,4 @@
import base64
import hashlib import hashlib
import itertools import itertools
import re import re
@ -337,57 +338,51 @@ def _extract_playlist(self, webpage):
return self.playlist_result(entries, album_id, album_title) return self.playlist_result(entries, album_id, album_title)
def _real_extract(self, url): def _real_extract(self, url):
webpage = self._download_webpage( js = self._download_webpage(
url, 'temp_id', note='download video page') 'https://mesh.if.iqiyi.com/player/lw/lwplay/accelerator.js?apiVer=3',
'temp_id_js',
headers={'Referer': url},
)
# There's no simple way to determine whether an URL is a playlist or not tvid = self._search_regex(r'"tvid":(\d+)', js, 'tvid')
# Sometimes there are playlist links in individual videos, so treat it
# as a single video first
tvid = self._search_regex(
r'data-(?:player|shareplattrigger)-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid', default=None)
if tvid is None:
playlist_result = self._extract_playlist(webpage)
if playlist_result:
return playlist_result
raise ExtractorError('Can\'t find any video')
video_id = self._search_regex( params = {
r'data-(?:player|shareplattrigger)-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id') 'tvid': tvid,
'ad_cid': '',
'disableDRM': 'false',
'cpt': 0,
'apiVer': 3,
'format': 'json',
'timestamp': int(time.time() * 1000),
}
formats = [] download_info = self._download_json(
for _ in range(5): 'https://mesh.if.iqiyi.com/player/lw/lwplay/accelerator.js', 'temp_id_json', query=params)
raw_data = self.get_raw_data(tvid, video_id) ev = download_info.get('ev')
if not ev:
raise ExtractorError('No ev data in response')
if raw_data['code'] != 'A00000': # Decode
if raw_data['code'] == 'A00111': try:
self.raise_geo_restricted() decoded = ''.join(chr(ord(c) ^ 90) for c in ev)
raise ExtractorError('Unable to load data. Error code: ' + raw_data['code']) ev_data = self._parse_json(decoded, 'ev json')
except Exception as e:
raise ExtractorError('Failed to decode ev: ' + str(e))
data = raw_data['data'] m3u8_content = traverse_obj(ev_data, ('data', 'program', 'video', 2, 'm3u8'))
m3u8_base64 = base64.b64encode(m3u8_content.encode('utf-8')).decode('ascii')
m3u8_data_url = f'data:application/vnd.apple.mpegurl;base64,{m3u8_base64}'
title = traverse_obj(download_info,('videoInfo','title'))
for stream in data['vidl']: formats = [{
if 'm3utx' not in stream: 'format_id': 'default',
continue 'url': m3u8_data_url,
vd = str(stream['vd']) 'ext': 'mp4',
formats.append({ 'protocol': 'm3u8_native',
'url': stream['m3utx'], }]
'format_id': vd,
'ext': 'mp4',
'quality': self._FORMATS_MAP.get(vd, -1),
'protocol': 'm3u8_native',
})
if formats:
break
self._sleep(5, video_id)
title = (get_element_by_id('widget-videotitle', webpage)
or clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage))
or self._html_search_regex(r'<span[^>]+data-videochanged-title="word"[^>]*>([^<]+)</span>', webpage, 'title'))
return { return {
'id': video_id, 'id': tvid,
'title': title, 'title': title,
'formats': formats, 'formats': formats,
} }