一个简单的爬虫源码

一个不正经的视频教学

import requests
import re
import time
headers&＃61;{&＃39;user-agent&＃39;:&＃39;Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36&＃39;}#Send the request
response&＃61;requests.get("https://mm.enterdesk.com/bizhi/62854-340754.html",headers&＃61;headers)
html&＃61;response.text
#print(html)#Parse the file
urls&＃61;re.findall(r&＃39; class&＃61;"pics_pics "\src&＃61;".*?"\href&＃61;".*?"><img\src&＃61;"(.*?)"\title&＃61;"双马尾美女青春迷人写真"/></a></div>\<div class&＃61;".*?"><a\&＃39;, html)
print(urls)#Save the page
for url in urls:time.sleep(30) # 延时1秒# 图片名字file_name &＃61; url.split(&＃39;/&＃39;)[-1] # 文件命名response &＃61; requests.get(url, headers&＃61;headers)with open(file_name, &＃39;wb&＃39;) as f: # 以2进制形式写入文件名f.write(response.content)