女朋友找我斗图,最后斗她到自闭。
网址:https://www.doutula.com/
难度不大,代码如下:
# -*- coding: utf-8 -*-
import random
import requests
from bs4 import BeautifulSoup
import urllib
import os
BASE_URL = 'https://www.doutula.com/photo/list/?page='
URL_LIST = []
for x in range(1, 2):
REAL_URL = BASE_URL+str(x)
URL_LIST.append(REAL_URL)
def get_url(url):
my_headers = [
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14",