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.
"""
从B站搜索结果中提取视频的BV号，
"""
import re
import requests
from common_headers import HEADERS
from concurrent . futures import ThreadPoolExecutor
def get_source ( page_num ) :
""" 获取B站搜索结果页的源码 """
get_url = (
f ' https://api.bilibili.com/x/web-interface '
f ' /wbi/search/type?__refresh__=true&_extra=& '
f ' context=&page= { page_num } &page_size=42&from_source=&from_spmid=333.337& '
' platform=pc&highlight=1&single_column=0&keyword=2024巴黎奥运会 '
' &qv_id=zaOudcC1LJI0GehR81nuNQEKktKQ2aP1&ad_resource=5654 '
' &source_tag=3&gaia_vtoken=&category_id=&search_type=video '
)
response = requests . get ( url = get_url , headers = HEADERS , timeout = 10 )
return response . text
def extract_bv ( source_html ) :
""" 从搜索结果的HTML源码中提取BV号 """
return re . findall ( ' " bvid " : " (.*?) " , " title " : " .*? ' , source_html )
def save_bv_to_file ( bv_list ) :
""" 将BV号保存到文件中 """
with open ( ' /output/bv_numbers.txt ' , ' a ' , encoding = ' utf-8 ' ) as f :
for bv in bv_list :
f . write ( bv + ' \n ' )
def process_pages ( page_range ) :
""" 并行处理多个页面 """
with ThreadPoolExecutor ( ) as executor :
results = list ( executor . map ( get_source , page_range ) )
return results
def main ( ) :
""" 主函数： """
counter = 0
page_range = range ( 1 , 9 )
html_sources = process_pages ( page_range )
for html_source in html_sources :
bvs = extract_bv ( html_source )
save_bv_to_file ( bvs )
counter + = len ( bvs )
if counter > = 300 :
break
print ( " BV号收集完成 " )
if __name__ == ' __main__ ' :
main ( )
