python爬虫下载某网站156个网页小游戏素材

有哪些游戏自己看吧↓
一波网页小游戏（摸鱼专用）
https://www.52pojie.cn/thread-1269936-1-1.html

 

懒得看代码的可以直接下载成品，分成了两个包
https://wwi.lanzoui.com/iwGxvgqiwzc
密码:d89r
https://wwi.lanzoui.com/i7WQvgqisqj
密码:dg3j

以下为python代码

 

import requestsfrom bs4 import BeautifulSoup
 
 
def get_Url(url):
    str_list = []
    content = requests.get(url).content
    soup = BeautifulSoup(content, \'lxml\')
    find = soup.find(\'span\', attrs={\'class\': \'current\'})
    sum = int(find.text.split(\'/\')[1])
    for i in range(sum):
        if i == 0:
            str_list.append(\'https://www.mycodes.net/166/\')
            continue
        str_list.append(\'https://www.mycodes.net/166/\' + str(i + 1) + \'.htm\')
    return str_list
 
 
def get_document(url):
    soup = BeautifulSoup(requests.get(url).content, \'lxml\')
    find_all = soup.find_all(\'a\', attrs={\'style\': \'color:#006BCD;font-size:14px;\'})
    a = \'\'
    for value in find_all:
        if a.__eq__(str(value[\'href\'])):
            continue
        a = value[\'href\']
        document = BeautifulSoup(requests.get(value[\'href\']).content, \'lxml\')
        text = document.find(\'td\', attrs={\'class\': \'a0\'}).text
        print(text+":")
        td_s = document.find_all(\'td\', attrs={\'class\': \'b1\'})
        for td in td_s:
            find = td.find(\'a\')
            if find is not None:
                print(find[\'href\'])
 
 
if __name__ == \'__main__\':
    url_list = get_Url(\'https://www.mycodes.net/166/\')
    for url in url_list:
        get_document(url)