n

nnnn
from multiprocessing.pool import Poolnimport requestsnimport renimport timen# 请求头nheaders = {n "Accept": "*/*",n "Accept-Encoding": "gzip, deflate, br",n "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",n "Cookie": "l=AurqcPuigwQdnQv7WvAfCoR1OlrRQW7h; isg=BHp6mNB79CHqYXpVEiRteXyyyKNcg8YEwjgLqoRvCI3ddxqxbLtOFUBGwwOrZ3ad; thw=cn; cna=VsJQERAypn0CATrXFEIahcz8; t=0eed37629fe7ef5ec0b8ecb6cd3a3577; tracknick=tb830309_22; _cc_=UtASsssmfA%3D%3D; tg=0; ubn=p; ucn=unzbyun; x=e%3D1%26p%3D*%26s%3D0%26c%3D0%26f%3D0%26g%3D0%26t%3D0%26__ll%3D-1%26_ato%3D0; miid=981798063989731689; hng=CN%7Czh-CN%7CCNY%7C156; um=0712F33290AB8A6D01951C8161A2DF2CDC7C5278664EE3E02F8F6195B27229B88A7470FD7B89F7FACD43AD3E795C914CC2A8BEB1FA88729A3A74257D8EE4FBBC; enc=1UeyOeN0l7Fkx0yPu7l6BuiPkT%2BdSxE0EqUM26jcSMdi1LtYaZbjQCMj5dKU3P0qfGwJn8QqYXc6oJugH%2FhFRA%3D%3D; ali_ab=58.215.20.66.1516409089271.6; mt=ci%3D-1_1; cookie2=104f8fc9c13eb24c296768a50cabdd6e; _tb_token_=ee7e1e1e7dbe7; v=0",n "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64;` rv:46.0) Gecko/20100102 Firefox/46.0"n}ndef getUrls(url):n resp = requests.request("GET", url, data='', headers=headers)n resp.encoding=resp.apparent_encodingn html_source = resp.textn urls = re.findall("https://[^>\";\']*\d",html_source)n us=[]n for url in urls:n if 'qq_43376286/article/details' in url:n if url not in us:n us.append(url)n return usndef thread_job(us):n while True:n for url in us:n requests.request("GET", url, data='', headers=headers)n print('您的' + url + '访问+1')n time.sleep(2)nif __name__ == '__main__':n urls = getUrls(r"https://blog.csdn.net/qq_43376286")n pool = Pool(processes=8)n result = pool.map(thread_job, (urls,))n pool.close() # 关闭进程池,不再接受新的进程n pool.join() # 主进程阻塞等待子进程的退出
n
Comments NOTHING