web crawling(plus6) more than one line

标签：bin   attr   urlopen   cep   code   pre   /usr   win   head   

#Author：Mini
#！/usr/bin/env python
import urllib.request
import re
import urllib.error
import threading
headers=("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36")
opener=urllib.request.build_opener()
opener.addheaders=[headers]
urllib.request.install_opener(opener)
try:
 class A(threading.Thread):
    def __init__(self):
      threading.Thread.__init__(self)
    def run(self):
        for i in range (1,10,2):
            print("line A!")
            url= "https://www.qiushibaike.com/hot/page/" + str(i) + "/"
            pagedata = urllib.request.urlopen(url).read().decode("utf-8","ignore")
            pat = ‘<div class="content"><span>(.*?)</span>‘
            datalist = re.compile(pat, re.S).findall(pagedata)
            for j in range(0, len(datalist)):
                print(str(i) + "." + str(j) + "content:")
                print(datalist[j])
 class B (threading.Thread):
    def __init__(self):
        threading.Thread.__init__(self)
    def run(self):
        for i in range(0,10,2):
            print("line B!")
            url="https://www.qiushibaike.com/hot/page/" + str(i) + "/"
            pagedata = urllib.request.urlopen(url)
            pagedata=pagedata.read().decode("utf-8","ignore")
            pat = ‘<div class="content"><span>(.*?)</span>‘
            datalist = re.compile(pat, re.S).findall(pagedata)
            for j in range(0, len(datalist)):
                print(str(i) + "." + str(j) + "content:")
                print(datalist[j])
 t1=A()
 t1.start()
 t2=B()
 t2.start()
except urllib.error.URLError as e:
    if hasattr(e, "code"):
        print(e.code)
    if hasattr(e, "reason"):
        print(e.reason)

web crawling(plus6) more than one line

标签：bin   attr   urlopen   cep   code   pre   /usr   win   head   

原文地址：http://www.cnblogs.com/rabbittail/p/7631942.html