Python_Spidder.rar_python 文件_python spidder

# -*- coding:utf-8 -*- import urllib.request as req import urllib import os import re write_file_path="C:\\Users\\testing\\Spider\\write_file\\" file_root_path="C:\\Users\\testing\\Spider\\root_folder\\" file_list=tuple(os.walk(file_root_path)) for file_name in file_list[0][2]: print(file_name) file_path=file_root_path+file_name file_object=open(file_path) try: file_content=file_object.read() restr = r'http://bbs.*?jpg' urllist = re.findall(restr,file_content,re.S) finally: file_object.close() #print(urllist) for url in urllist: if len(url)!=0: split_name=url.split('/')[-1] writed_file_name=write_file_path+split_name #print(writed_file_name) with open(writed_file_name, 'wb') as file: try: image_detail=req.urlopen(url, None, None).read() file.write(image_detail) except urllib.error.HTTPError as e: print(e.code) print(url)