爬取煎蛋网图片的一种思路
2018-09-07 本文已影响0人
cz_布衣
任何一个学习的过程，都需要练手项目。学网络爬虫就总会想去爬点什么东西。网上更多介绍的就是爬取网站图片，图片网站一般都有会自己的一套反爬技术。昨天遇到有帖子在说爬煎蛋网图片，也就去试了试。
其中的反爬技术分析在 Python爬虫(15):煎蛋网加密处理方式 博客中已有详细解说，思路方法也有说了，大家可以仔细去看看。在这里，我的思路也一样，但实现方法不是去将其js方法改造成为python方法（虽然我也觉得这是最佳方法，无奈我对加密算法不熟悉，代码理解不了。接下来还是得去学学加密的算法才行。）这里使用一个偷巧的办法，把js解密方法直接拿出来构造一个html文件，再把抓到的图片hash值放进去，让它来给我解密还原成地址。有了地址你想怎么下载就很容易了，我使用的是用迅雷。（爬取图片的hash：把个含图片的网页都下载，直接抓取各个<span class="img-hash">***</span>值）。
构造html文件时，我是截取jandan_load_img()中有关的两行代码，jdXFKzuIDxRVqKYQfswJ5elNfow1x0JrJH()就全照原样拷出来运行，然后打开开发者工具，边运行边看出现什么错误，需要什么方法就去原网站的js中寻找并补齐。除了hex_md5()外，其它方法都可以在原网站的js中找到。百度了一下，hex_md5()函数是在md5.js中，我下边也给我整个md5.js文件。（hex_md5()本来也是想拷贝出来用就好，可是看到md5.js里边好多参数，若是拷出来不知会涉及多少其它东西，所以就干脆直接引用md5.js）。
先上图：
html.png
抓取图片hash值的py代码如下：
图片hash都存放到img_hash.txt中
# -*- coding:utf-8 -*-
from lxml import etree
import requests, time
urls = ['http://jandan.net/ooxx/page-{}#comments'.format(i) for i in range(1, 41)]
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko)'
' Chrome/22.0.1207.1 Safari/537.1'}
i = 1
img_hash = []
print('Downloading:', end='')
for url in urls:
html = requests.get(url, headers=headers).text
root = etree.HTML(html)
span_img_hashs = root.xpath('//span[@class="img-hash"]')
for span_img_hash in span_img_hashs:
img_hash.append(span_img_hash.text)
print(i, '\t', end='')
i += 1
time.sleep(3)
print('Download completed!')
with open('img_hash.txt', 'a') as f:
f.write(str(img_hash))
html文件如下：
- get_url()函数是我加上去的，将hash值作为参数调用jandan_load_img()
- 打开img_hash.txt，将其中的hash值拷贝给get_url()函数的hashlist变量
<!DOCTYPE html>
<html>
<head>
<title></title>
<script type="text/ecmascript" src="md5.js"></script>
<script type="text/javascript">
function jandan_load_img(e) {
var c = jdjDMYMvK51QlNY6NdLY1OkZw6dpQvspIM(e, "aPz8sQnzRxiHfhgesalhIBhfKZczglYq");
var a = c.replace(/(\/\/\w+\.sinaimg\.cn\/)(\w+)(\/.+\.(gif|jpg|jpeg))/, "$1large$3");
return a
}
var jdjDMYMvK51QlNY6NdLY1OkZw6dpQvspIM = function(o, y, g) {
var d = o;
var l = "DECODE";
var y = y ? y : "";
var g = g ? g : 0;
var h = 4;
y = md5(y);
var x = md5(y.substr(0, 16));
var v = md5(y.substr(16, 16));
if (h) {
if (l == "DECODE") {
var b = md5(microtime());
var e = b.length - h;
var u = b.substr(e, h)
}
} else {
var u = ""
}
var t = x + md5(x + u);
var n;
if (l == "DECODE") {
g = g ? g + time() : 0;
tmpstr = g.toString();
if (tmpstr.length >= 10) {
o = tmpstr.substr(0, 10) + md5(o + v).substr(0, 16) + o
} else {
var f = 10 - tmpstr.length;
for (var q = 0; q < f; q++) {
tmpstr = "0" + tmpstr
}
o = tmpstr + md5(o + v).substr(0, 16) + o
}
n = o
}
var k = new Array(256);
for (var q = 0; q < 256; q++) {
k[q] = q
}
var r = new Array();
for (var q = 0; q < 256; q++) {
r[q] = t.charCodeAt(q % t.length)
}
for (var p = q = 0; q < 256; q++) {
p = (p + k[q] + r[q]) % 256;
tmp = k[q];
k[q] = k[p];
k[p] = tmp
}
var m = "";
n = n.split("");
for (var w = p = q = 0; q < n.length; q++) {
w = (w + 1) % 256;
p = (p + k[w]) % 256;
tmp = k[w];
k[w] = k[p];
k[p] = tmp;
m += chr(ord(n[q]) ^ (k[(k[w] + k[p]) % 256]))
}
if (l == "DECODE") {
m = base64_encode(m);
var c = new RegExp("=","g");
m = m.replace(c, "");
m = u + m;
m = base64_decode(d)
}
return m
};
function md5(a) {
return hex_md5(a)
}
function base64_encode(a) {
return window.btoa(a)
}
function base64_decode(a) {
return window.atob(a)
}
function microtime(b) {
var a = new Date().getTime();
var c = parseInt(a / 1000);
return b ? (a / 1000) : (a - (c * 1000)) / 1000 + " " + c
}
function chr(a) {
return String.fromCharCode(a)
}
function ord(a) {
return a.charCodeAt()
}
function get_url() {
var hashlist = ['Ly93eDQuc2luYWltZy5jbi9tdzYwMC8wMDc2QlNTNWx5MWZ1am93MDQyNGJqMzBpYTB0M3dnMi5qcGc=', 'Ly93dzMuc2luYWltZy5jbi9tdzEwMjQvMDA3M29iNlBneTFmdWpvNWdodGNiZzMwNnkwYW11MHkuZ2lm', 'Ly93eDQuc2luYWltZy5jbi9tdzYwMC8wMDc2QlNTNWx5MWZ1am5teGpqdWdqMzExMTFqazRxcC5qcGc='];
// var urllist = new Array()
var content = '';
for (hash in hashlist){
var url = 'http:' + jandan_load_img(hashlist[hash]);
// urllist[hash] = url;
content += '<a href="'+url+'">'+url+'</a>';
content += '<br>'
}
document.getElementById("content").innerHTML = content;
}
</script>
</head>
<body>
<button onclick="get_url()">click here</button>
<div id="content"></div>
</body>
</html>
md5.js：
/*
* A JavaScript implementation of the RSA Data Security, Inc. MD5 Message
* Digest Algorithm, as defined in RFC 1321.
* Version 2.1 Copyright (C) Paul Johnston 1999 - 2002.
* Other contributors: Greg Holt, Andrew Kepert, Ydnar, Lostinet
* Distributed under the BSD License
* See http://pajhome.org.uk/crypt/md5 for more info.
*/
/*
* Configurable variables. You may need to tweak these to be compatible with
* the server-side, but the defaults work in most cases.
*/
var hexcase = 0; /* hex output format. 0 - lowercase; 1 - uppercase */
var b64pad = ""; /* base-64 pad character. "=" for strict RFC compliance */
var chrsz = 8; /* bits per input character. 8 - ASCII; 16 - Unicode */
/*
* These are the functions you'll usually want to call
* They take string arguments and return either hex or base-64 encoded strings
*/
function hex_md5(s){ return binl2hex(core_md5(str2binl(s), s.length * chrsz));}
function b64_md5(s){ return binl2b64(core_md5(str2binl(s), s.length * chrsz));}
function str_md5(s){ return binl2str(core_md5(str2binl(s), s.length * chrsz));}
function hex_hmac_md5(key, data) { return binl2hex(core_hmac_md5(key, data)); }
function b64_hmac_md5(key, data) { return binl2b64(core_hmac_md5(key, data)); }
function str_hmac_md5(key, data) { return binl2str(core_hmac_md5(key, data)); }
/*
* Perform a simple self-test to see if the VM is working
*/
function md5_vm_test()
{
return hex_md5("abc") == "900150983cd24fb0d6963f7d28e17f72";
}
/*
* Calculate the MD5 of an array of little-endian words, and a bit length
*/
function core_md5(x, len)
{
/* append padding */
x[len >> 5] |= 0x80 << ((len) % 32);
x[(((len + 64) >>> 9) << 4) + 14] = len;
var a = 1732584193;
var b = -271733879;
var c = -1732584194;
var d = 271733878;
for(var i = 0; i < x.length; i += 16)
{
var olda = a;
var oldb = b;
var oldc = c;
var oldd = d;
a = md5_ff(a, b, c, d, x[i+ 0], 7 , -680876936);
d = md5_ff(d, a, b, c, x[i+ 1], 12, -389564586);
c = md5_ff(c, d, a, b, x[i+ 2], 17, 606105819);
b = md5_ff(b, c, d, a, x[i+ 3], 22, -1044525330);
a = md5_ff(a, b, c, d, x[i+ 4], 7 , -176418897);
d = md5_ff(d, a, b, c, x[i+ 5], 12, 1200080426);
c = md5_ff(c, d, a, b, x[i+ 6], 17, -1473231341);
b = md5_ff(b, c, d, a, x[i+ 7], 22, -45705983);
a = md5_ff(a, b, c, d, x[i+ 8], 7 , 1770035416);
d = md5_ff(d, a, b, c, x[i+ 9], 12, -1958414417);
c = md5_ff(c, d, a, b, x[i+10], 17, -42063);
b = md5_ff(b, c, d, a, x[i+11], 22, -1990404162);
a = md5_ff(a, b, c, d, x[i+12], 7 , 1804603682);
d = md5_ff(d, a, b, c, x[i+13], 12, -40341101);
c = md5_ff(c, d, a, b, x[i+14], 17, -1502002290);
b = md5_ff(b, c, d, a, x[i+15], 22, 1236535329);
a = md5_gg(a, b, c, d, x[i+ 1], 5 , -165796510);
d = md5_gg(d, a, b, c, x[i+ 6], 9 , -1069501632);
c = md5_gg(c, d, a, b, x[i+11], 14, 643717713);
b = md5_gg(b, c, d, a, x[i+ 0], 20, -373897302);
a = md5_gg(a, b, c, d, x[i+ 5], 5 , -701558691);
d = md5_gg(d, a, b, c, x[i+10], 9 , 38016083);
c = md5_gg(c, d, a, b, x[i+15], 14, -660478335);
b = md5_gg(b, c, d, a, x[i+ 4], 20, -405537848);
a = md5_gg(a, b, c, d, x[i+ 9], 5 , 568446438);
d = md5_gg(d, a, b, c, x[i+14], 9 , -1019803690);
c = md5_gg(c, d, a, b, x[i+ 3], 14, -187363961);
b = md5_gg(b, c, d, a, x[i+ 8], 20, 1163531501);
a = md5_gg(a, b, c, d, x[i+13], 5 , -1444681467);
d = md5_gg(d, a, b, c, x[i+ 2], 9 , -51403784);
c = md5_gg(c, d, a, b, x[i+ 7], 14, 1735328473);
b = md5_gg(b, c, d, a, x[i+12], 20, -1926607734);
a = md5_hh(a, b, c, d, x[i+ 5], 4 , -378558);
d = md5_hh(d, a, b, c, x[i+ 8], 11, -2022574463);
c = md5_hh(c, d, a, b, x[i+11], 16, 1839030562);
b = md5_hh(b, c, d, a, x[i+14], 23, -35309556);
a = md5_hh(a, b, c, d, x[i+ 1], 4 , -1530992060);
d = md5_hh(d, a, b, c, x[i+ 4], 11, 1272893353);
c = md5_hh(c, d, a, b, x[i+ 7], 16, -155497632);
b = md5_hh(b, c, d, a, x[i+10], 23, -1094730640);
a = md5_hh(a, b, c, d, x[i+13], 4 , 681279174);
d = md5_hh(d, a, b, c, x[i+ 0], 11, -358537222);
c = md5_hh(c, d, a, b, x[i+ 3], 16, -722521979);
b = md5_hh(b, c, d, a, x[i+ 6], 23, 76029189);
a = md5_hh(a, b, c, d, x[i+ 9], 4 , -640364487);
d = md5_hh(d, a, b, c, x[i+12], 11, -421815835);
c = md5_hh(c, d, a, b, x[i+15], 16, 530742520);
b = md5_hh(b, c, d, a, x[i+ 2], 23, -995338651);
a = md5_ii(a, b, c, d, x[i+ 0], 6 , -198630844);
d = md5_ii(d, a, b, c, x[i+ 7], 10, 1126891415);
c = md5_ii(c, d, a, b, x[i+14], 15, -1416354905);
b = md5_ii(b, c, d, a, x[i+ 5], 21, -57434055);
a = md5_ii(a, b, c, d, x[i+12], 6 , 1700485571);
d = md5_ii(d, a, b, c, x[i+ 3], 10, -1894986606);
c = md5_ii(c, d, a, b, x[i+10], 15, -1051523);
b = md5_ii(b, c, d, a, x[i+ 1], 21, -2054922799);
a = md5_ii(a, b, c, d, x[i+ 8], 6 , 1873313359);
d = md5_ii(d, a, b, c, x[i+15], 10, -30611744);
c = md5_ii(c, d, a, b, x[i+ 6], 15, -1560198380);
b = md5_ii(b, c, d, a, x[i+13], 21, 1309151649);
a = md5_ii(a, b, c, d, x[i+ 4], 6 , -145523070);
d = md5_ii(d, a, b, c, x[i+11], 10, -1120210379);
c = md5_ii(c, d, a, b, x[i+ 2], 15, 718787259);
b = md5_ii(b, c, d, a, x[i+ 9], 21, -343485551);
a = safe_add(a, olda);
b = safe_add(b, oldb);
c = safe_add(c, oldc);
d = safe_add(d, oldd);
}
return Array(a, b, c, d);
}
/*
* These functions implement the four basic operations the algorithm uses.
*/
function md5_cmn(q, a, b, x, s, t)
{
return safe_add(bit_rol(safe_add(safe_add(a, q), safe_add(x, t)), s),b);
}
function md5_ff(a, b, c, d, x, s, t)
{
return md5_cmn((b & c) | ((~b) & d), a, b, x, s, t);
}
function md5_gg(a, b, c, d, x, s, t)
{
return md5_cmn((b & d) | (c & (~d)), a, b, x, s, t);
}
function md5_hh(a, b, c, d, x, s, t)
{
return md5_cmn(b ^ c ^ d, a, b, x, s, t);
}
function md5_ii(a, b, c, d, x, s, t)
{
return md5_cmn(c ^ (b | (~d)), a, b, x, s, t);
}
/*
* Calculate the HMAC-MD5, of a key and some data
*/
function core_hmac_md5(key, data)
{
var bkey = str2binl(key);
if(bkey.length > 16) bkey = core_md5(bkey, key.length * chrsz);
var ipad = Array(16), opad = Array(16);
for(var i = 0; i < 16; i++)
{
ipad[i] = bkey[i] ^ 0x36363636;
opad[i] = bkey[i] ^ 0x5C5C5C5C;
}
var hash = core_md5(ipad.concat(str2binl(data)), 512 + data.length * chrsz);
return core_md5(opad.concat(hash), 512 + 128);
}
/*
* Add integers, wrapping at 2^32. This uses 16-bit operations internally
* to work around bugs in some JS interpreters.
*/
function safe_add(x, y)
{
var lsw = (x & 0xFFFF) + (y & 0xFFFF);
var msw = (x >> 16) + (y >> 16) + (lsw >> 16);
return (msw << 16) | (lsw & 0xFFFF);
}
/*
* Bitwise rotate a 32-bit number to the left.
*/
function bit_rol(num, cnt)
{
return (num << cnt) | (num >>> (32 - cnt));
}
/*
* Convert a string to an array of little-endian words
* If chrsz is ASCII, characters >255 have their hi-byte silently ignored.
*/
function str2binl(str)
{
var bin = Array();
var mask = (1 << chrsz) - 1;
for(var i = 0; i < str.length * chrsz; i += chrsz)
bin[i>>5] |= (str.charCodeAt(i / chrsz) & mask) << (i%32);
return bin;
}
/*
* Convert an array of little-endian words to a string
*/
function binl2str(bin)
{
var str = "";
var mask = (1 << chrsz) - 1;
for(var i = 0; i < bin.length * 32; i += chrsz)
str += String.fromCharCode((bin[i>>5] >>> (i % 32)) & mask);
return str;
}
/*
* Convert an array of little-endian words to a hex string.
*/
function binl2hex(binarray)
{
var hex_tab = hexcase ? "0123456789ABCDEF" : "0123456789abcdef";
var str = "";
for(var i = 0; i < binarray.length * 4; i++)
{
str += hex_tab.charAt((binarray[i>>2] >> ((i%4)*8+4)) & 0xF) +
hex_tab.charAt((binarray[i>>2] >> ((i%4)*8 )) & 0xF);
}
return str;
}
/*
* Convert an array of little-endian words to a base-64 string
*/
function binl2b64(binarray)
{
var tab = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
var str = "";
for(var i = 0; i < binarray.length * 4; i += 3)
{
var triplet = (((binarray[i >> 2] >> 8 * ( i %4)) & 0xFF) << 16)
| (((binarray[i+1 >> 2] >> 8 * ((i+1)%4)) & 0xFF) << 8 )
| ((binarray[i+2 >> 2] >> 8 * ((i+2)%4)) & 0xFF);
for(var j = 0; j < 4; j++)
{
if(i * 8 + j * 6 > binarray.length * 32) str += b64pad;
else str += tab.charAt((triplet >> 6*(3-j)) & 0x3F);
}
}
return str;
}
如果本文对您有帮助，请给我留个言。谢谢！
