python爬虫学习第一天：50行代码爬取“精美”壁纸，哈哈哈哈

说明：记录一下自己爬虫的学习过程 嘻嘻……

前提：
安装 requests模块，re模块，time模块

代码如下：

import requests
import re
import time

def get_url(url, text='src'):
    headers = {'User-Agent':
                   'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 '
                   'Safari/537.36'}
    res = requests.get(url, headers=headers, timeout=5)
    if text == 'src':
        res.encoding = res.apparent_encoding
        return res.text
    return res.content

def get_str_list(start_text, end_text, text):
    start = text.find(start_text) + len(start_text)
    end = text.find(end_text)
    return text[start:end]

def data_cleaning(src_list, regular, condition):
    pattern = re.compile(regular)
    src = re.findall(pattern, src_list)
    src_list = [i for i in src if i.find(condition) > 0]
    return src_list

def save_img(img_text):
    with open(f'{(time.time())}.jpg', 'wb') as f:
        f.write(img_text)
        print("save success")
    
def format_img(text):
    start_text = '<div class="list">'
    end_text = '<div class="page">'
    str_list = get_str_list(start_text, end_text, text)

    src_list = data_cleaning(str_list, 'href="(.*?)"', 'desk')
    for src in src_list:
        url = f'http://www.netbian.com{src}'
        text = get_url(url, 'src')
        str_list = get_str_list('<div class="pic">', '<div class="pic-down">', text)
        src_list = data_cleaning(str_list, 'img src="(.*?)"', 'jpg')
        for img in src_list:
            img_text = get_url(img, 'img')
            save_img(img_text)

def main():
    for index in range(1, 10):
        if index == 1:
            url = f'http://www.netbian.com/meinv/index.htm'
        else:
            url = f'http://www.netbian.com/meinv/index_{index}.htm'
        text = get_url(url)
        format_img(text)

if __name__ == '__main__':
    main()