PYTHON 爬虫 baidu美女图片

2023年4月8日 103次阅读 
from urllib import request
import re 
import os
def main():
 #page=request.urlopen("http://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fr=&sf=1&fmq=1461834053046_R&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&itg=0&ie=utf-8&word=%E5%A4%B4%E5%83%8F#z=0&pn=&ic=0&st=-1&face=0&s=0&lm=-1" )  
# "https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=index&fr=&hs=0&xthttps=111111&sf=1&fmq=&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&word=%E4%B8%AD%E5%9B%BD&oq=%E4%B8%AD%E5%9B%BD&rsp=-1")    
page = request.urlopen("https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=index&fr=&hs=0&xthttps=111111&sf=1&fmq=&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&word=%E7%BE%8E%E5%A5%B3&oq=%E7%BE%8E%E5%A5%B3&rsp=-1") 
context=page.read().decode('utf-8') 
pic=re.findall("https://.*?jpg",context) 
count = 0; # 文件的起始名称为 0  
for url in pic: 
print(url) 
bytes = request.urlopen(url); 
if (url.find('.') != -1): # 2  
 name =url[url.find('.', len(url) - 5):]; 
 f = open("D:/image/" + str(count) + name, 'wb'); # 代开一个文件，准备以二进制写入文件  
 f.write(bytes.read()); # write并不是直接将数据写入文件，而是先写入内存中特定的缓冲区  
 f.flush(); # 将缓冲区的数据立即写入缓冲区，并清空缓冲区  
 f.close(); # 关闭文件  
 count += 1;
if __name__ == '__main__':
main()
点赞