爬qqhentai

import requests
from bs4 import BeautifulSoup
import time
import re
import os
import random

agentlist = ["Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36","Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0","Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0","Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50"]



def get_nomal_headers():
    headers = {
        "User-Agent":random.choice(agentlist)
    }
    # print(headers)
    return headers
def get_pages():
    url1 = "https://zh.qqhentai.com/g/334792/list2/cdnwp/"
    headers = get_nomal_headers()
    r = requests.get(url1,headers = headers)
    soup = BeautifulSoup(r.text,"html.parser")
    # print(soup)
    container  = soup.find("section",id="image-container")
    img_list = container.find_all("img",class_="list-img lazyload")
    # print(img_list)
    for i in img_list:
        page = i["alt"]
        page = ''.join(page.split(" "))
        imgurl = i["data-src"]

        downloadimg(page,imgurl)

def downloadimg(page,imgurl):
    imgpath = (page + ".jpg")
    if os.path.exists(imgpath):
        print("已存在"+page + ".jpg")
        pass
    else:
        headers = get_nomal_headers()
        r = requests.get(imgurl,headers = headers)
        print("downloading"+page)
        fin = open(imgpath, "wb")
        fin.write(r.content)
        fin.flush()
        time.sleep(0.2)

get_pages()