pufei漫画网GET请求解密

你的名字 2022-01-12 05:33 72阅读 0赞

网站地址m.pufei.net，追更的有《驭灵师》、《狐妖小红娘》、《一人之下》、《戒魔人》

去年就写过它的爬虫，因为那会儿完全不懂js，所以是用selenium爬的，效率很低。

### 主要的解密代码 ###

import execjs
    
    cp = 'ZXZhbChmdW5jdGlvbihwLGEsYyxrLGUsZCl7ZT1mdW5jdGlvbihjKXtyZXR1cm4gYy50b1N0cmluZygzNil9O2lmKCEnJy5yZXBsYWNlKC9eLyx' \
         'TdHJpbmcpKXt3aGlsZShjLS0pe2RbYy50b1N0cmluZyhhKV09a1tjXXx8Yy50b1N0cmluZyhhKX1rPVtmdW5jdGlvbihlKXtyZXR1cm4gZFtlXX' \
         '1dO2U9ZnVuY3Rpb24oKXtyZXR1cm4nXFx3Kyd9O2M9MX07d2hpbGUoYy0tKXtpZihrW2NdKXtwPXAucmVwbGFjZShuZXcgUmVnRXhwKCdcXGInK' \
         '2UoYykrJ1xcYicsJ2cnKSxrW2NdKX19cmV0dXJuIHB9KCdkPVtcJzQvMi8xLzMvYy41LzBcJyxcJzQvMi8xLzMvYS41LzBcJyxcJzQvMi8xLzMv' \
         'OS41LzBcJyxcJzQvMi8xLzMvNi41LzBcJyxcJzQvMi8xLzMvNy41LzBcJyxcJzQvMi8xLzMvOC41LzBcJyxcJzQvMi8xLzMvYi41LzBcJyxcJzQ' \
         'vMi8xLzMvai41LzBcJyxcJzQvMi8xLzMvay41LzBcJyxcJzQvMi8xLzMvZS41LzBcJyxcJzQvMi8xLzMvaS41LzBcJyxcJzQvMi8xLzMvaC41Lz' \
         'BcJyxcJzQvMi8xLzMvZi41LzBcJyxcJzQvMi8xLzMvZy41LzBcJ10nLDIxLDIxLCd8Mjl8MDV8MDB8MjAxOXxqcGd8NTFiMjFkYzk1M3w1MWFiM' \
         'Tc3NWRjfDUxNGM0YjU5ZTB8NTE1NDQ5NDU0YXw1MWRiMGE3Y2NhfDUxNTEzYjViMzB8NTFlYjA1ZjE1NHxfY3VSc3w1MWI1YzVkNjVmfDUxYjc4' \
         'MDkxMTZ8NTE4ZDQyNjAyZXw1MTY2ODQxZjljfDUxNTQ2NTk5ODh8NTEzMGJiMDBkNnw1MWJjYzAxODJmJy5zcGxpdCgnfCcpLDAse30pKQo='
    
    
    def get_urls(c_p):
        js_code = ''' function base64decode(str) { var base64EncodeChars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; var base64DecodeChars = new Array(-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 62, -1, -1, -1, 63, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, -1, -1, -1, -1, -1, -1, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, -1, -1, -1, -1, -1); var c1, c2, c3, c4; var i, len, out; len = str.length; i = 0; out = ""; while (i < len) { do { c1 = base64DecodeChars[str.charCodeAt(i++) & 255] } while (i < len && c1 == -1); if (c1 == -1) { break } do { c2 = base64DecodeChars[str.charCodeAt(i++) & 255] } while (i < len && c2 == -1); if (c2 == -1) { break } out += String.fromCharCode((c1 << 2) | ((c2 & 48) >> 4)); do { c3 = str.charCodeAt(i++) & 255; if (c3 == 61) { return out } c3 = base64DecodeChars[c3] } while (i < len && c3 == -1); if (c3 == -1) { break } out += String.fromCharCode(((c2 & 15) << 4) | ((c3 & 60) >> 2)); do { c4 = str.charCodeAt(i++) & 255; if (c4 == 61) { return out } c4 = base64DecodeChars[c4] } while (i < len && c4 == -1); if (c4 == -1) { break } out += String.fromCharCode(((c3 & 3) << 6) | c4) } return out } function geturl(cp) { value = eval(eval(base64decode(cp).slice(4))); return value } '''
        js_context = execjs.compile(js_code)
        return js_context.call('geturl', c_p)
    
    
    if __name__ == '__main__':
        print(get_urls(cp))
    复制代码

返回的结果是一章里所有漫画的url

['2019/05/29/00/51eb05f154.jpg/0', '2019/05/29/00/51db0a7cca.jpg/0', '2019/05/29/00/515449454a.jpg/0', '2019/05/29/00/51b21dc953.jpg/0', '2019/05/29/00/51ab1775dc.jpg/0', '2019/05/29/00/514c4b59e0.jpg/0', '2019/05/29/00/51513b5b30.jpg/0', '2019/05/29/00/5130bb00d6.jpg/0', '2019/05/29/00/51bcc0182f.jpg/0', '2019/05/29/00/51b5c5d65f.jpg/0', '2019/05/29/00/5154659988.jpg/0', '2019/05/29/00/5166841f9c.jpg/0', '2019/05/29/00/51b7809116.jpg/0', '2019/05/29/00/518d42602e.jpg/0']
    复制代码

参数cp在网页源代码里，使用正则提取，然后字符串切片

cp="\w+.* 复制代码

下一篇我会写出完整的爬取过程，并附上代码 [juejin.im/post/5cfe1b…][juejin.im_post_5cfe1b]

转载于:https://juejin.im/post/5cf6272df265da1bd260d8ce

[juejin.im_post_5cfe1b]: https://juejin.im/post/5cfe1b59f265da1bb13f2646