You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.
import requests
import re
import random
import time
# headers = {'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Mobile Safari/537.36 Edg/128.0.0.0'}
headers = {
" user-agent " : " Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.5735.289 Safari/537.36 " ,
" Cookie " : " i-wanna-go-back=-1; buvid_fp_plain=undefined; CURRENT_BLACKGAP=0; blackside_state=0; LIVE_BUVID=AUTO5216539051785441; buvid4=BF640363-932C-9859-2DEB-9D5332BED8BA14521-022050118-RBQaCti2N %2F gbXXvSImVESA % 3D % 3D; buvid3=EA6B6EE5-CF42-44F0-8BF1-0E035F5182C9167646infoc; DedeUserID=506881997; DedeUserID__ckMd5=6816981dbd4223e9; CURRENT_FNVAL=4048; rpdid=|(u))kRlJJ)u0J ' uYY)l~u)~J; CURRENT_QUALITY=80; hit-new-style-dyn=1; CURRENT_PID=150df130-cdea-11ed-9e61-390f799e5bb1; _uuid=68159E9C-3BA8-49EE-A1C6-D7E510610D865E40530infoc; nostalgia_conf=-1; b_ut=5; FEED_LIVE_VERSION=V8; hit-dyn-v2=1; home_feed_column=5; browser_resolution=1530-712; header_theme_version=CLOSE; fingerprint=93340026c1ba350713aeadf8766000e1; SESSDATA=5c25a608 % 2C1709466512 % 2Cc7e4b % 2A92gDhsEFKTVzRobJkJtk9Sk1ph71ufczEtnhZVk3UyXcKE4ChKGDta46HuRUO_g-u_Rbl2OgAAYQA; bili_jct=37f8d40c6076352e8e44a85bbbeb65a4; sid=7px9659x; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE2OTQxODU3MzksImlhdCI6MTY5MzkyNjUzOSwicGx0IjotMX0.ek0FRkjhs25UswbCHtI0R25Otecvf_5FppkCkYoDMCE; bili_ticket_expires=1694185739; PVID=3; b_nut=100; buvid_fp=93340026c1ba350713aeadf8766000e1; b_lsid=109D53E510_18A6AC7C071; bp_video_offset_506881997=838254238965432390 " ,
}
def get_info ( url ) :
sleep_time = random . randint ( 0 , 3 ) + random . random ( )
time . sleep ( sleep_time )
response = requests . get ( url = url , headers = headers )
response . encoding = response . apparent_encoding #改变编码
# 解析数据（
data_list = re . findall ( ' <d p= " .*? " >(.*?)</d> ' , response . text )
#输出到文件
tot = 0
for index in data_list :
with open ( ' ./danmu.txt ' , mode = ' a ' , encoding = ' utf-8 ' ) as f :
f . write ( index )
f . write ( ' \n ' )
tot = tot + 1
return tot
if __name__ == ' __main__ ' :
cnt = 0
tot = 0
with open ( ' ./cid.txt ' , ' r ' ) as file :
for line in file :
cid = line . strip ( )
tot + = get_info ( ' https://api.bilibili.com/x/v1/dm/list.so?oid= ' + cid )
cnt = cnt + 1
print ( f " danmu : { cnt } /300, { tot } " )
