今日头条的街拍下载实现 python

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from time import sleep
import requests
import threading
import os
import re


def gethtml(url):

    chrome_options = Options()
    chrome_options.add_argument('--headless')
    chrome_options.add_argument('--disable-gpu')
    #上面是设置无界浏览器用的，不用打开浏览器也可以爬取数据！
    chrome_options.add_experimental_option('excludeSwitches', ['enable-automation'])
    #对chrome开启开发者模式
    driver = webdriver.Chrome(options=chrome_options)
    # 设置无头浏览器，就是隐藏界面后台运行
    driver.get(url)
    driver.refresh()# 有验证码，刷新一下，就好了
    sleep(3)
    #等浏览器反应3秒钟，设置沉睡，否则加载不到我们想要的数据！

    soup = driver.page_source
    driver.close()
    driver.quit()

    return soup

def parserurl(soup):
    tapm = re.compile('<div id="(.*?)".*?href="/group/(.*?)">')
    htmldata=re.findall(tapm,soup)
    return htmldata

def geturls(html):
    temp = re.compile('<img src="(http.*?)"')
    pict = re.findall(temp, html)
    print(pict)
    return pict


# def getpicurl():
# def getpict():
#     pass

def main():
    url='https://www.toutiao.com/search/?keyword=%E8%A1%97%E6%8B%8D'
    url_1='https://www.toutiao.com/'
    html=gethtml(url)
    htmlurl=parserurl(html)


    data=[]
    filname=[]
    dataurl=[]
    print(dataurl)
    for i in range(len(htmlurl)):
        filname.append(htmlurl[i][0])
        dataurl.append(url_1+'a'+htmlurl[i][1])
    for j in range(len(filname)):
        pict=gethtml(dataurl[j])
        urls=geturls(pict)
        a={filname[j]:urls}
        data.append(a)
    print(filname)
        #多线程开始
    class A(threading.Thread):
        def __init__(self):
                threading.Thread.__init__(self)
        def run(self):
            for k in range(0, len(data), 2):
                os.chdir("E:\桌面\\222")
                os.mkdir(filname[k])
                m = len(data[k][filname[k]])
                for n in range(m):
                    with open('E:/桌面/222/' + filname[k] + '/' + str(n + 1) + '.jpg', 'wb') as f:
                        req = requests.get(data[k][filname[k]][n])
                        datapic = req.content
                        f.write(datapic)
                        f.close()

    class B(threading.Thread):
        def __init__(self):
            threading.Thread.__init__(self)

        def run(self):
            for k in range(1, len(data), 2):
                os.chdir("E:\桌面\\222")
                os.mkdir(filname[k])
                m = len(data[k][filname[k]])
                for n in range(m):

                    with open('E:/桌面/222/' + filname[k] + '/' + str(n + 1) + '.jpg', 'wb') as f:
                        req = requests.get(data[k][filname[k]][n])
                        datapic = req.content
                        f.write(datapic)
                        f.close()

    t1 = A()
    t1.start()
    t2 = B()
    t2.start()
main()