selenium爬堆糖网壁纸

身为二刺螈真的一看到动漫手绘美图就想保存下来啊，堆糖上有很多好看的插画，试着用selenium爬了一下，并保存到本地。

# coding--utf8
import selenium
import time
from selenium.webdriver.common.keys import Keys
from selenium import webdriver
import requests

import os
import sys
sys.setrecursionlimit(100000)


#爬取堆糖插画
#def driver
options = webdriver.ChromeOptions()
# 更换头部，这一步好像没什么用，每页有120张图片，最后只能爬86张，不知道什么原因啊？？头秃
options.add_argument('user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36"')
driver = webdriver.Chrome(options=options,executable_path="C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe")


def q(page_num):
    return f'https://www.duitang.com/category/?cat=painting#!hot-p{page_num}'


def scroll_pages(html):
    html = driver.find_element_by_tag_name('html')
    for i in range(10):
        html.send_keys(Keys.END)
        time.sleep(1)

def get_img_url():
    links = driver.find_elements_by_css_selector('div.mbpho>a>img')
    for link in links:
        src = str(link.get_attribute('src')).split('.')
        del src[-2]
        del src[-2]
        img_url = src[0] + "." + src[1] + '.' + src[2] + '.' + src[3]
        print(img_url)
        if os.path.exists('illustration') is False:
            os.mkdir('illustration')
        img_name = img_url.split('/')[-1]
        filename = os.path.join('illustration', img_name)
        r = requests.get(img_url)
        with open(filename, "wb") as f:
            f.write(r.content)

for i in range(1,85):
    q(i)
    driver.get(q(i))
    scroll_pages(q(i))
    get_img_url()
    time.sleep(10)

运行结果如下：

麻麻再也不用担心我没有手机壁纸了呢！！