python爬虫练习——爬取壁纸

main.py

import requests
from bs4 import BeautifulSoup
import os
import lib.tools as t
import time

def main():
    for i in range(1,11):
        bz_url = f"https://desk.zol.com.cn/pc/{i}.html"
        list = get_bz_list(bz_url)
        for page_url in list:
            get_bz_src(page_url)
            time.sleep(1)


def get_bz_list(bz_url):
    r = requests.get(bz_url)
    r.encoding = "gb2312"
    html = r.text
    soup=BeautifulSoup(html,'lxml')
    a_list = soup.select(".pic-list2")[0].select(".pic")
    list = []
    for h in a_list:
        if os.path.splitext(h.attrs["href"])[-1] == ".html":
            list.append("https://desk.zol.com.cn" + h.attrs["href"])
    return list


def get_bz_src(page_url):
    r = requests.get(page_url)
    r.encoding = "gb2312"
    html = r.text
    soup=BeautifulSoup(html,'lxml')
    pic_div = soup.select("div[class='wrapper photo-tit clearfix']")
    title_name = pic_div[0].select("a[id='titleName']")[0].get_text()
    max_num = t.getmidstring(html, '<span>（<span class="current-num">1</span>/', "）</span>")
    src = soup.select("img[id='bigImg']")[0].attrs["src"]
    pic_name = title_name + os.path.splitext(src)[-1]
    t.down_pic(src,f"bz_save/{pic_name}")
    print(f"{pic_name}------下载完成")


    


if __name__ == "__main__":
    main()

tools.py

import requests
import os
import glob

# 取出中间文本
def getmidstring(html, start_str, end):
    start = html.find(start_str)
    if start >= 0:
        start += len(start_str)
        end = html.find(end, start)
        if end >= 0:
            return html[start:end].strip()

# 下载图片
def down_pic(img_url,path):
    reponse = requests.get(img_url)
    with open(path,'wb') as f:
        f.write(reponse.content)

# 创建文件夹
# 遇到重复文件夹命名为文件夹目录_1(2,3,4……)
# 返回文件夹目录名称
def mkdir(path,root_flag=False):
    folder = os.path.exists(path)
    floder_path = path
    if not folder:
        os.makedirs(path)
    else:
        if not root_flag:
            num_p = 1
            sub_path = glob.glob(path + '*')
            if sub_path:
                # 最后一个创建目录
                last_path = sub_path[-1]
                floder_path = last_path + '_{}'.format(num_p)
                if last_path.find('_') > 0:
                    num_str = last_path.split('_')
                    if num_str[-1].isdigit():
                        num_p = int(num_str[-1]) + 1
                        floder_path = last_path[0:last_path.rfind(
                            '_')] + '_{}'.format(num_p)
                        os.makedirs(floder_path)
                    else:
                        os.makedirs(floder_path)
                else:
                    os.makedirs(floder_path)
    return floder_path

结果：