python多线程爬取_python-爬虫12-多线程爬取

可复制代码如下：

###多线程

import re

import threading

import urllib.request

import urllib.error

import threading

headers=("User-Agent","Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36")

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):

print("我是线程One")

for i in range(1,20,2):

url='https://www.qiushibaike.com/text/page/'

urla=url+str(i)

data=urllib.request.urlopen(urla).read().decode("utf-8","ignore")

pat='

.*? (.*?).*?

'

datalist=re.compile(pat,re.S).findall(data)

for j in range(0,len(datalist)):

print("第"+str(i)+"页第"+str(j)+"个段子的内容")

print(datalist[j])

class Two(threading.Thread):

def __init__(self):

threading.Thread.__init__(self)

def run(self):

print("我是线程Two")

for i in range(0,20,2):

url='https://www.qiushibaike.com/text/page/'

urla=url+str(i)

data=urllib.request.urlopen(urla).read().decode("utf-8","ignore")

pat='

.*? (.*?).*?

'

datalist=re.compile(pat,re.S).findall(data)

for j in range(0,len(datalist)):

print("第"+str(i)+"页第"+str(j)+"个段子的内容")

print(datalist[j])

one=One()

one.start()

two=Two()

two.start()