复制

# -*- coding: UTF-8 -*-
import json
import requests
import base64

def xigua(url):
headers={
"cookie": "ixigua-a-s=0; __ac_nonce=062711eef0074c53fd301; "
"__ac_signature=_02B4Z6wo00f01ixJMjwAAIDDB8Np-ahvLqYsaTaAAOlxwFWsX1Khk-KvFlM1N2JBoEUa-eVrLxEyF"
".bLdz61qjeQ-CTdvApqa7NKn7HTvbu1Nktww-QaXyO3gNQSkIdrfp3XdUkGrdCwrQKpea; "
"MONITOR_WEB_ID=6364cae8-2aa7-4531-9a30-1b98b0ee7596; "
"ttwid=1%7CTOw3V-1qPgQfcCT4S0Hhey26Q4PJq9J6nGaLq6GMe14%7C1651580656"
"%7C48653bc0c5afd31f1a919f9bd17a80173a1ea69d96b23359b103c4f078ef969b; support_webp=true; "
"support_avif=true; _tea_utm_cache_1300=undefined",
"Referer": "https://www.ixigua.com",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/86.0.4240.75 Safari/537.36"
}
resp=requests.get(url=url,headers=headers)
resp.encoding='utf-8'
if resp.status_code==200:
res_html=resp.text
if 'pseries_more_v2' not in url:
json_str=re.findall('window._SSR_HYDRATED_DATA=(.*?)</script>', res_html)[0]
json_str=json_str.replace('undefined', 'null')
json_data=json.loads(json_str)
video_url=\
json_data['anyVideo']['gidInformation']['packerData']['video']['videoResource']['dash'][
'dynamic_video'][
'dynamic_video_list'][-1]['main_url']
audio_url=\
json_data['anyVideo']['gidInformation']['packerData']['video']['videoResource']['dash'][
'dynamic_video'][
'dynamic_audio_list'][-1]['main_url']
title=json_data['anyVideo']['gidInformation']['packerData']['video']['title']
title=re.sub(r"[/\\\:\*\?"\<\>\|]", "_", title).replace(" ", "")
video_url=base64.b64decode(video_url).decode()
audio_url=base64.b64decode(audio_url).decode()
print(video_url)
print(audio_url)
print(title)
else:
json_data=json.loads(res_html)
for item in json_data['data']:
title=item['title']
# backup_url_1
video_url=item['preloadVideoResource']['dynamic_video']['dynamic_video_list'][-1][
'backup_url_1']
audio_url=item['preloadVideoResource']['dynamic_video']['dynamic_audio_list'][-1][
'backup_url_1']
video_url=base64.b64decode(video_url).decode()
audio_url=base64.b64decode(audio_url).decode()
title=re.sub(r"[/\\\:\*\?"\<\>\|]", "_", title).replace(" ", "")
print(video_url)
print(audio_url)
print(title)

xigua(url)