python爬虫-多线程

最新推荐文章于 2024-07-10 18:18:26 发布

yinger_0131

最新推荐文章于 2024-07-10 18:18:26 发布

阅读量392

点赞数

分类专栏： python 爬虫文章标签： python 爬虫多线程

本文链接：https://blog.csdn.net/yinger_0131/article/details/79537364

版权

python 爬虫专栏收录该内容

5 篇文章 0 订阅

订阅专栏

import urllib.request
import threading
import re
import urllib.error
headers=("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.22 Safari/537.36 SE 2.X MetaSr 1.0")
opener=urllib.request.build_opener()
opener.addheaders=[headers]
urllib.request.install_opener(opener)
class One(threading.Thread):
    def __init__(self):
        threading.Thread.__init__(self)
    def run(self):
        for i in range(1,10,2):  #奇数页
            url="http://www.qiushibaike.com/8hr/page/"+str(i)
            pagedata=urllib.request.urlopen(url).read().decode("utf-8","ignore")
            pat='<div class="content">.*?<span>(.*?)</span>.*?</div>'
            datalist=re.compile(pat,re.S).findall(pagedata)
            for j in range(0,len(datalist)):
                print("第"+str(i)+"页第"+str(j)+"个段子的内容是：")
                print(datalist[j])
class Two(threading.Thread):
    def __init__(self):
        threading.Thread.__init__(self)
    def run(self):
        for i in range(0,36,2):
            url="http://www.qiushibaike.com/8hr/page/"+str(i)
            pagedata=urllib.request.urlopen(url).read().decode("utf-8","ignore")
            pat='<div class="content">.*?<span>(.*?)</span>.*?</div>'
            datalist=re.compile(pat,re.S).findall(pagedata)
            for j in range(0,len(datalist)):
                print("第"+str(i)+"页第"+str(j)+"个段子的内容是：")
                print(datalist[j])

#开启线程（先实例化再start）                
one=One()
one.start()
two=Two()
two.start()