[Python知识库]包图网1.2

from selenium import webdriver
from selenium.webdriver import ChromeOptions
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
import time
from bs4 import BeautifulSoup
import re
import os
from selenium.webdriver.common.action_chains import ActionChains
import requests
import zipfile
import schedule

def get_photos(start_pos):
    option = ChromeOptions()
    option.add_experimental_option('excludeSwitches', ['enable-automation'])
    option.add_argument("--disable-blink-features")
    option.add_argument("--disable-blink-features=AutomationControlled")
    desired_capabilities = DesiredCapabilities.CHROME
    desired_capabilities["pageLoadStrategy"] = "none"

    # 打开谷歌浏览器
    driver = webdriver.Chrome(options=option)
    # 打开网页
    driver.get('https://ibaotu.com/sy/17-0-0-0-0-112.html')
    # 为div弹框，直接是与定位其他元素一样，直接进行定位（'class name'）
    # 点击登录
    driver.find_element_by_css_selector(
        'body > header.b-header.b-header-float-fixed.b-header-classify.header-have-boxshodow.b-header-fixed--no > div > div.b-header-right.clearfix > div:nth-child(4) > div > p').click()

    # 浏览器窗口切换？切换到 QQ
    current_window = driver.window_handles
    # print(current_window)
    driver.implicitly_wait(5)
    driver.switch_to.window(current_window[0])
    time.sleep(2)
    driver.find_element_by_css_selector(
        'body > div.re-popbox.reg-pop.login-New > div > div.login-in-way.clearfix > a.in-way-WX.ibaotu-md-click.auth-type-QQ.btn-social-login-item').click()
    # driver.get_screenshot_as_file ("D:/1.PNG")

    # 再次切换到网页内部的iframe窗口
    current_window1 = driver.window_handles
    # print(current_window1)
    driver.switch_to.window(current_window1[1])
    driver.switch_to.frame(0)
    driver.find_element_by_css_selector('#switcher_plogin').click()

    # 登陆进去
    username = '351916740'
    password = '920825ZlyTC10'
    time.sleep(3)
    driver.switch_to.window(current_window1[1])
    driver.switch_to.frame(0)  # 再一次踩坑，登录框框有iframe，需要先进入到iframe，再去定位
    driver.find_element_by_css_selector('#u').send_keys(username)
    time.sleep(2)
    driver.find_element_by_css_selector('#p').send_keys(password)
    time.sleep(3)
    driver.find_element_by_id("login_button").click()
    time.sleep(3)

    # 验证条解锁

    # 窗口切换到包图网
    current_window2 = driver.window_handles
    # print(current_window2)
    driver.switch_to.window(current_window[0])

    all_window_height = []  # 创建一个列表，用于记录每一次拖动滚动条后页面的最大高度
    all_window_height.append(driver.execute_script("return document.body.scrollHeight;"))  # 当前页面的最大高度加入列表
    while True:
        driver.execute_script("scroll(0,15000)")  # 执行拖动滚动条操作
        time.sleep(3)
        check_height = driver.execute_script("return document.body.scrollHeight;")
        if check_height == all_window_height[-1]:  # 判断拖动滚动条后的最大高度与上一次的最大高度的大小，相等表明到了最底部
            break
        else:
            all_window_height.append(check_height)  # 如果不想等，将当前页面最大高度加入列表。

    # 解析数据部分
    driver.enconding = 'UTF-8'
    soup = BeautifulSoup(driver.page_source, 'html.parser')  # 得到全部的element代码
    body = soup.find('div', attrs={'class': 'skin-wrap body-background-gradient'})
    body = body.find('div',
                     attrs={'class': 'search-list box-bg-search box-bottom-gradient clearfix'})  # find只会找到与它内容匹配的第一个
    body = body.find_all('div', attrs={'class': 'hover-pop'})
    dwonload_url_list = []

    for hover in body:
        a_label = hover.find('a')
        A_label_content = a_label['href']
        txt_url = 'https:' + a_label['href']
        pattern = re.compile(r'\d+')
        id = pattern.findall(A_label_content)[0]
        str_id = str(id)
        dwonload_url = 'https:' + '//ibaotu.com/?m=downloadopen&a=open&id=' + str_id + '&down_type=1&&attachment_id=&zt_size_type=0'
        dwonload_url_list.append(dwonload_url)

    for i in range(start_pos-1,start_pos-21,-1):
        time.sleep(2)
        driver.get(dwonload_url_list[i])
        time.sleep(5)

    #解压
    global count
    for filename in os.listdir('D:/download/'):
        r = zipfile.is_zipfile('D:/download/'+ filename)
        print(r)
        if r:
            fz = zipfile.ZipFile('D:/download/'+ filename, 'r')
            for file in fz.namelist():
                dst_dir = 'D:/' + str(count)

                fz.extract(file, dst_dir)
                count += 1
        else:
            print('This is not zip')



def lenth(length):
    le=length-20
    return le
def calulate_day(day):
    while day<4:
        global length
        le=lenth(length)
        print(le)
        length=le
        get_photos(length)
        day += 1
        time.sleep(5)
    else:
        return


if __name__ == "__main__":
    length=100
    day=0
    count=0
    calulate_day(day)