爬取糗事百科的图片

Posted 2020-09-22 月下柳梢映

小编，最近写了个单线程的爬虫，主要是爬取糗事百科的图片之类的，下面是源代码，小伙伴们可以拿去参照，学习


#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests,json
import requests,re,os,time
import urllib.request
import urllib.parse
import ssl
import unittest
from selenium import webdriver

headers = {"User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;"}
os.chdir("meizhu")
def fc(url):

      req = urllib.request.Request(url, headers = headers)
      html = urllib.request.urlopen(req).read().decode(‘utf-8‘)

      r =‘<img src="//(.+?\.jpg)" alt="[\u4e00-\u9fa5]{1,}"/>‘
      result = re.compile(r).findall(str(html))
      
      h=(list(result))
      print(h)

      for img in h:
         imgurl ="http://" + img
         imaname = str(img.split(‘/‘)[4]+".jpg")
         file = urllib.request.urlretrieve(str(imgurl),filename=imaname)

for i in range(1,5):
   url = "http://www.qiushibaike.com/pic/page/" + str(i)
   fc(url)