python抓取wallhaven首页壁纸

python抓取wallhaven首页壁纸

"""
下载wallheaven首页图片，保存在同级文件夹image中
"""
from bs4 import BeautifulSoup
import requests
import re
import os

"""
图片下载函数
Pic_url为图片的url
save_path为图片保存路径
Headers为请求头,有默认参数
"""


# noinspection PyDefaultArgument
def DownloadImage(Pic_url, Save_path, Headers={
    "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                  'Chrome/83.0.4103.61 Safari/537.36 '
}):
    if not os.path.exists(Save_path):
        os.mkdir(Save_path)
    pic_name = pic_url[-20:]
    pic = requests.get(url=Pic_url, headers=Headers)
    with open(Save_path + pic_name, 'wb') as f:
        for chunk in pic.iter_content():
            f.write(chunk)
    print("图片已保存")


if __name__ == '__main__':
    # wallhaven的网址
    url = "https://wallhaven.cc/"
    # 请求头，用于通过wallhaven的检查，wallhaven不支持爬虫爬取
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/83.0.4103.61 Safari/537.36 '
    }
    # 获取html文件
    response = requests.get(url=url, headers=headers)
    html = BeautifulSoup(response.text, 'html5lib')
    # 获取每一张图片的高清图片链接，存入列表。由于从上一个页面获取到的链接是打开图片详情页的链接，所以在这再次发起请求。
    pic_page_url_list = []
    for item in html.find_all(name='a', href=re.compile("https://wallhaven.cc/w/")):
        pic_page_url_list.append(item.get("href"))
    # 逐一下载列表里面的图片
    for pic_page_url in pic_page_url_list:
        pic_response = requests.get(url=pic_page_url, headers=headers)
        pic_html = BeautifulSoup(pic_response.text, 'html5lib')
        pic_url = pic_html.select('#wallpaper')[0]["src"]
        if pic_url:
            print(pic_url)
            DownloadImage(pic_url, 'image/', headers)
        else:
            print("No url")