Python自学记录--多线程糗事百科爬虫 - 精易论坛

#线程库
import threading
#队列
import queue
import requests
import time
from lxml import etree
#采集网页线程--爬取段子列表所在的网页，放进队列
class Thread1(threading.Thread):
def __init__(self, threadName,pageQueue,dataQueue):
threading.Thread.__init__(self)
self.threadName = threadName #线程名
self.pageQueue = pageQueue #页码队列
self.dataQueue = dataQueue #数据队列
self.headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"}
def run(self):
print("启动线程"+self.threadName)
while not flag1:
try:
page=self.pageQueue.get()
url="https://www.qiushibaike.com/8hr/page/"+str(page)+"/"
content=requests.get(url,headers=self.headers).text
time.sleep(0.5)
self.dataQueue.put(content) #将数据放入队列中
except Exception as e:
pass
print("结束线程"+self.threadName)
#解析网页线程--从队列中拿到列表网页，进行解析，并储存到本地
class Thread2(threading.Thread):
def __init__(self, threadName,dataQueue,filename):
threading.Thread.__init__(self)
self.threadName = threadName
self.dataQueue = dataQueue
self.filename = filename
def run(self):
print("启动线程"+self.threadName)
while not flag2:
try:
data1=self.dataQueue.get()
html=etree.HTML(data1)
node_list=html.xpath('//div//a[@class="recmd-content"]')
for node in node_list:
data=node.text
self.filename.write(data+"\n")
except Exception as e:
pass
print("结束线程"+self.threadName)
flag1=False #判断页码队列中是否为空
flag2=False #判断数据队列中是否为空
def main():
#页码队列
pageQueue=queue.Queue(2) #页码最大为10
for i in range(1,11):
pageQueue.put(i)
#存放采集结果的数据队列
dataQueue=queue.Queue()
#保存到本地的文件
filename=open(r"D:\代码保存\duanzi.txt","a")
#启动线程
t1=Thread1("采集线程",pageQueue,dataQueue)
t1.start()
t2=Thread2("解析线程",dataQueue,filename)
t2.start()
#当padeQueue为空时，结束采集线程
while not pageQueue.empty():
pass
global flag1
flag1=True
#当padeQueue为空时，结束采集线程
while not pageQueue.empty():
pass
global flag2
flag2=True
t1.join()
t2.join()
filename.close()
print("结束！")
if __name__ == '__main__':
main()

复制代码