通过urllib.request.Request(Url)请求网站,BeautifulSoup解析返回的二进制内容,re.findall()匹配图片地址
最终print(get_list)打印出了图片地址的一个列表
3. 通过python调用,下载图片,以下是Test_Down.py的内容
通过urllib.request.Request(image_url)获取图片,然后写入本地,看到路径下多了一张图片,说明整个爬虫实现是可实现的
4. 综合上面分析,写出完整爬虫代码 douban_spider.py
1 from urllib import request
2 from urllib.request import urlopen
3 from bs4 import BeautifulSoup
4 import os
5 import time
6 import re
7 import threading
8
9
10 # 全局声明的可以写到配置文件,这里为了读者方便看,故只写在一个文件里面
11 # 图片地址
12 picpath = r'E:\Python_Doc\Images'
13 # 豆瓣地址
14 douban_url = "https://www.dbmeinv.com/dbgroup/show.htm?cid=%s&pager_offset=%s"
15
16
17 # 保存路径的文件夹,没有则自己创建文件夹,不能创建上级文件夹
18 def setpath(name):
19 path = os.path.join(picpath, name)
20 if not os.path.isdir(path):
21 os.mkdir(path)
22 return path
23
24
25 # 获取html内容
26 def get_html(url):
27 req = request.Request(url)
28 return request.urlopen(req).read()
29
30
31 # 获取图片地址
32 def get_ImageUrl(html):
33 data = BeautifulSoup(html, "lxml")
34 r = r'(https://\S+\.jpg)'
35 p = re.compile(r)
36 return re.findall(p, str(data))
37
38
39 # 保存图片
40 def save_image(savepath, url):
41 content = urlopen(url).read()
42 # url[-11:] 表示截取原图片后面11位
43 with open(savepath + '/' + url[-11:], 'wb') as code:
44 code.write(content)
45
46
47 def do_task(savepath, cid, index):
48 url = douban_url % (cid, index)
49 html = get_html(url)
50 image_list = get_ImageUrl(html)
51 # 此处判断其实意义不大,程序基本都是人手动终止的,因为图片你是下不完的
52 if not image_list:
53 print(u'已经全部抓取完毕')
54 return
55 # 实时查看,这个有必要
56 print("=============================================================================")
57 print(u'开始抓取Cid= %s 第 %s 页' % (cid, index))
58 for image in image_list:
59 save_image(savepath, image)
60 # 抓取下一页
61 do_task(savepath, cid, index+1)
62
63
64 if __name__ == '__main__':
65 # 文件名
66 filename = "DouBan"
67 filepath = setpath(filename)
68
69 # 2-胸 3-腿 4-脸 5-杂 6-臀 7-袜子
70 for i in range(2, 8):
71 do_task(filepath, i, 1)
72
73 # threads = []
74 # for i in range(2, 4):
75 # ti = threading.Thread(target=do_task, args=(filepath, i, 1, ))
76 # threads.append(ti)
77 # for t in threads:
78 # t.setDaemon(True)
79 # t.start()
80 # t.join()
View Code
运行程序,进入文件夹查看,图片已经不停的写入电脑了!
5. 分析:豆瓣图片下载用比较简单的爬虫就能实现,网站唯一的控制好像只有不能频繁调用,所以豆瓣不适合用多线程调用
from urllib import request
2 import re
3 from bs4 import BeautifulSoup
4
5
6 def get_html(url):
7 req = request.Request(url)
8 return request.urlopen(req).read()
9
10
11 if __name__ == '__main__':
12 url = "http://www.mm131.com/xinggan/list_6_2.html"
13 html = get_html(url)
14 data = BeautifulSoup(html, "lxml")
15 p = r"(http://www\S*/\d{4}\.html)"
16 get_list = re.findall(p, str(data))
17 # 循化人物地址
18 for i in range(20):
19 # print(get_list[i])
20 # 循环人物的N页图片
21 for j in range(200):
22 url2 = get_list[i][:-5] + "_" + str(j + 2) + ".html"
23 try:
24 html2 = get_html(url2)
25 except:
26 break
27 p = r"(http://\S*/\d{4}\S*\.jpg)"
28 get_list2 = re.findall(p, str(html2))
29 print(get_list2[0])
30 break
3. 下载图片 Test_Down.py,用豆瓣下载的方法下载,发现不论下载多少张,都是一样的下面图片
这个就有点尴尬了,妹子图片地址都有了,就是不能下载,浏览器打开的时候也是时好时坏,网上也找不到原因,当然楼主最终还是找到原因了,下面先贴上代码
1 from urllib import request
2 import requests
3
4
5 def get_image(url):
6 req = request.Request(url)
7 get_img = request.urlopen(req).read()
8 with open('E:/Python_Doc/Images/DownTest/123.jpg', 'wb') as fp:
9 fp.write(get_img)
10 print("Download success!")
11 return
12
13
14 def get_image2(url_ref, url):
15 headers = {"Referer": url_ref,
16 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 '
17 '(KHTML, like Gecko)Chrome/62.0.3202.94 Safari/537.36'}
18 content = requests.get(url, headers=headers)
19 if content.status_code == 200:
20 with open('E:/Python_Doc/Images/DownTest/124.jpg', 'wb') as f:
21 for chunk in content:
22 f.write(chunk)
23 print("Download success!")
24
25
26 if __name__ == '__main__':
27 url_ref = "http://www.mm131.com/xinggan/2343_3.html"
28 url = "http://img1.mm131.me/pic/2343/3.jpg"
29 get_image2(url_ref, url)
可以看到下载成功,改用requests.get方法获取图片内容,这种请求方法方便设置头文件headers(urllib.request怎么设置headers没有研究过),headers里面有个Referer参数,必须设置为此图片的进入地址,从浏览器F12代码可以看出来,如下图
4. 测试都通过了,下面是汇总的完整源码
1 from urllib import request
2 from urllib.request import urlopen
3 from bs4 import BeautifulSoup
4 import os
5 import time
6 import re
7 import requests
8
9
10 # 全局声明的可以写到配置文件,这里为了读者方便看,故只写在一个文件里面
11 # 图片地址
12 picpath = r'E:\Python_Doc\Images'
13 # mm131地址
14 mm_url = "http://www.mm131.com/xinggan/list_6_%s.html"
15
16
17 # 保存路径的文件夹,没有则自己创建文件夹,不能创建上级文件夹
18 def setpath(name):
19 path = os.path.join(picpath, name)
20 if not os.path.isdir(path):
21 os.mkdir(path)
22 return path
23
24
25 # 获取html内容
26 def get_html(url):
27 req = request.Request(url)
28 return request.urlopen(req).read()
29
30
31 def save_image2(path, url_ref, url):
32 headers = {"Referer": url_ref,
33 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 '
34 '(KHTML, like Gecko)Chrome/62.0.3202.94 Safari/537.36'}
35 content = requests.get(url, headers=headers)
36 if content.status_code == 200:
37 with open(path + '/' + str(time.time()) + '.jpg', 'wb') as f:
38 for chunk in content:
39 f.write(chunk)
40
41
42 def do_task(path, url):
43 html = get_html(url)
44 data = BeautifulSoup(html, "lxml")
45 p = r"(http://www\S*/\d{1,5}\.html)"
46 get_list = re.findall(p, str(data))
47 # print(data)
48 # 循化人物地址 每页20个
49 for i in range(20):
50 try:
51 print(get_list[i])
52 except:
53 break
54 # 循环人物的N页图片
55 for j in range(200):
56 url2 = get_list[i][:-5] + "_" + str(3*j + 2) + ".html"
57 try:
58 html2 = get_html(url2)
59 except:
60 break
61 p = r"(http://\S*/\d{1,4}\S*\.jpg)"
62 get_list2 = re.findall(p, str(html2))
63 save_image2(path, get_list[i], get_list2[0])
64
65
66 if __name__ == '__main__':
67 # 文件名
68 filename = "MM131_XG"
69 filepath = setpath(filename)
70
71 for i in range(2, 100):
72 print("正在List_6_%s " % i)
73 url = mm_url % i
74 do_task(filepath, url)
View Code
运行程序后,图片将源源不断的写入电脑
5. 分析:MM131图片下载主要问题是保存图片的时候需要用headers设置Referer
1 ......
2 <div class="text">
3 <span class="righttext">
4 <a href="//jandan.net/ooxx/page-2#comment-3535967">3535967</a>
5 </span>
6 <p>
7 <img src="//img.jandan.net/img/blank.gif" onload="jandan_load_img(this)" />
8 <span class="img-hash">d0c4TroufRLv8KcPl0CZWwEuhv3ZTfJrTVr02gQHSmnFyf0tWbjze3F+DoWRsMEJFYpWSXTd5YfOrmma+1CKquxniG2C19Gzh81OF3wz84m8TSGr1pXRIA</span>
9 </p>
10 </div>
11 ......
从上面关键结果可以看到,<span class="img-hash">后面的一长串哈希字符才是图片地址,网站打开时候动态转换位图片地址显示的,这个时候只想说三个字MMP
不过上有政策,下有对策,那就把这些hash字符串转为图片地址了,怎么转呢? 以下提供两种方案
(1)通过Python的execjs模块直接调用JS里面的函数,将这个hash转为图片地址,具体实现就是把当前网页保存下来,然后找到里面的js转换方法函数,单独拎出来写在一个JS里面
调用的JS和方法如下:OOXX1.js CallJS.python
1 function OOXX1(a,b) {
2 return md5(a)
3 }
4 function md5(a) {
5 return "Success" + a
6 }
1 import execjs
2
3
4 # 执行本地的js
5 def get_js():
6 f = open("OOXX1.js", 'r', encoding='UTF-8')
7 line = f.readline()
8 htmlstr = ''
9 while line:
10 htmlstr = htmlstr + line
11 line = f.readline()
12 return htmlstr
13
14
15 js = get_js()
16 ctx = execjs.compile(js)
17 ss = "SS"
18 cc = "CC"
19 print(ctx.call("OOXX1", ss, cc))
此种方法只提供思路,楼主找到的JS如下 OOXX.js,实际调用报错了,这个方法应该会比方法二速度快很多,所以还是贴上未完成代码供读者参阅研究
1 function time() {
2 var a = new Date().getTime();
3 return parseInt(a / 1000)
4 }
5 function microtime(b) {
6 var a = new Date().getTime();
7 var c = parseInt(a / 1000);
8 return b ? (a / 1000) : (a - (c * 1000)) / 1000 + " " + c
9 }
10 function chr(a) {
11 return String.fromCharCode(a)
12 }
13 function ord(a) {
14 return a.charCodeAt()
15 }
16 function md5(a) {
17 return hex_md5(a)
18 }
19 function base64_encode(a) {
20 return btoa(a)
21 }
22 function base64_decode(a) {
23 return atob(a)
24 } (function(g) {
25 function o(u, z) {
26 var w = (u & 65535) + (z & 65535),
27 v = (u >> 16) + (z >> 16) + (w >> 16);
28 return (v << 16) | (w & 65535)
29 }
30 function s(u, v) {
31 return (u << v) | (u >>> (32 - v))
32 }
33 function c(A, w, v, u, z, y) {
34 return o(s(o(o(w, A), o(u, y)), z), v)
35 }
36 function b(w, v, B, A, u, z, y) {
37 return c((v & B) | ((~v) & A), w, v, u, z, y)
38 }
39 function i(w, v, B, A, u, z, y) {
40 return c((v & A) | (B & (~A)), w, v, u, z, y)
41 }
42 function n(w, v, B, A, u, z, y) {
43 return c(v ^ B ^ A, w, v, u, z, y)
44 }
45 function a(w, v, B, A, u, z, y) {
46 return c(B ^ (v | (~A)), w, v, u, z, y)
47 }
48 function d(F, A) {
49 F[A >> 5] |= 128 << (A % 32);
50 F[(((A + 64) >>> 9) << 4) + 14] = A;
51 var w, z, y, v, u, E = 1732584193,
52 D = -271733879,
53 C = -1732584194,
54 B = 271733878;
55 for (w = 0; w < F.length; w += 16) {
56 z = E;
57 y = D;
58 v = C;
59 u = B;
60 E = b(E, D, C, B, F[w], 7, -680876936);
61 B = b(B, E, D, C, F[w + 1], 12, -389564586);
62 C = b(C, B, E, D, F[w + 2], 17, 606105819);
63 D = b(D, C, B, E, F[w + 3], 22, -1044525330);
64 E = b(E, D, C, B, F[w + 4], 7, -176418897);
65 B = b(B, E, D, C, F[w + 5], 12, 1200080426);
66 C = b(C, B, E, D, F[w + 6], 17, -1473231341);
67 D = b(D, C, B, E, F[w + 7], 22, -45705983);
68 E = b(E, D, C, B, F[w + 8], 7, 1770035416);
69 B = b(B, E, D, C, F[w + 9], 12, -1958414417);
70 C = b(C, B, E, D, F[w + 10], 17, -42063);
71 D = b(D, C, B, E, F[w + 11], 22, -1990404162);
72 E = b(E, D, C, B, F[w + 12], 7, 1804603682);
73 B = b(B, E, D, C, F[w + 13], 12, -40341101);
74 C = b(C, B, E, D, F[w + 14], 17, -1502002290);
75 D = b(D, C, B, E, F[w + 15], 22, 1236535329);
76 E = i(E, D, C, B, F[w + 1], 5, -165796510);
77 B = i(B, E, D, C, F[w + 6], 9, -1069501632);
78 C = i(C, B, E, D, F[w + 11], 14, 643717713);
79 D = i(D, C, B, E, F[w], 20, -373897302);
80 E = i(E, D, C, B, F[w + 5], 5, -701558691);
81 B = i(B, E, D, C, F[w + 10], 9, 38016083);
82 C = i(C, B, E, D, F[w + 15], 14, -660478335);
83 D = i(D, C, B, E, F[w + 4], 20, -405537848);
84 E = i(E, D, C, B, F[w + 9], 5, 568446438);
85 B = i(B, E, D, C, F[w + 14], 9, -1019803690);
86 C = i(C, B, E, D, F[w + 3], 14, -187363961);
87 D = i(D, C, B, E, F[w + 8], 20, 1163531501);
88 E = i(E, D, C, B, F[w + 13], 5, -1444681467);
89 B = i(B, E, D, C, F[w + 2], 9, -51403784);
90 C = i(C, B, E, D, F[w + 7], 14, 1735328473);
91 D = i(D, C, B, E, F[w + 12], 20, -1926607734);
92 E = n(E, D, C, B, F[w + 5], 4, -378558);
93 B = n(B, E, D, C, F[w + 8], 11, -2022574463);
94 C = n(C, B, E, D, F[w + 11], 16, 1839030562);
95 D = n(D, C, B, E, F[w + 14], 23, -35309556);
96 E = n(E, D, C, B, F[w + 1], 4, -1530992060);
97 B = n(B, E, D, C, F[w + 4], 11, 1272893353);
98 C = n(C, B, E, D, F[w + 7], 16, -155497632);
99 D = n(D, C, B, E, F[w + 10], 23, -1094730640);
100 E = n(E, D, C, B, F[w + 13], 4, 681279174);
101 B = n(B, E, D, C, F[w], 11, -358537222);
102 C = n(C, B, E, D, F[w + 3], 16, -722521979);
103 D = n(D, C, B, E, F[w + 6], 23, 76029189);
104 E = n(E, D, C, B, F[w + 9], 4, -640364487);
105 B = n(B, E, D, C, F[w + 12], 11, -421815835);
106 C = n(C, B, E, D, F[w + 15], 16, 530742520);
107 D = n(D, C, B, E, F[w + 2], 23, -995338651);
108 E = a(E, D, C, B, F[w], 6, -198630844);
109 B = a(B, E, D, C, F[w + 7], 10, 1126891415);
110 C = a(C, B, E, D, F[w + 14], 15, -1416354905);
111 D = a(D, C, B, E, F[w + 5], 21, -57434055);
112 E = a(E, D, C, B, F[w + 12], 6, 1700485571);
113 B = a(B, E, D, C, F[w + 3], 10, -1894986606);
114 C = a(C, B, E, D, F[w + 10], 15, -1051523);
115 D = a(D, C, B, E, F[w + 1], 21, -2054922799);
116 E = a(E, D, C, B, F[w + 8], 6, 1873313359);
117 B = a(B, E, D, C, F[w + 15], 10, -30611744);
118 C = a(C, B, E, D, F[w + 6], 15, -1560198380);
119 D = a(D, C, B, E, F[w + 13], 21, 1309151649);
120 E = a(E, D, C, B, F[w + 4], 6, -145523070);
121 B = a(B, E, D, C, F[w + 11], 10, -1120210379);
122 C = a(C, B, E, D, F[w + 2], 15, 718787259);
123 D = a(D, C, B, E, F[w + 9], 21, -343485551);
124 E = o(E, z);
125 D = o(D, y);
126 C = o(C, v);
127 B = o(B, u)
128 }
129 return [E, D, C, B]
130 }
131 function p(v) {
132 var w, u = "";
133 for (w = 0; w < v.length * 32; w += 8) {
134 u += String.fromCharCode((v[w >> 5] >>> (w % 32)) & 255)
135 }
136 return u
137 }
138 function j(v) {
139 var w, u = [];
140 u[(v.length >> 2) - 1] = undefined;
141 for (w = 0; w < u.length; w += 1) {
142 u[w] = 0
143 }
144 for (w = 0; w < v.length * 8; w += 8) {
145 u[w >> 5] |= (v.charCodeAt(w / 8) & 255) << (w % 32)
146 }
147 return u
148 }
149 function k(u) {
150 return p(d(j(u), u.length * 8))
151 }
152 function e(w, z) {
153 var v, y = j(w),
154 u = [],
155 x = [],
156 A;
157 u[15] = x[15] = undefined;
158 if (y.length > 16) {
159 y = d(y, w.length * 8)
160 }
161 for (v = 0; v < 16; v += 1) {
162 u[v] = y[v] ^ 909522486;
163 x[v] = y[v] ^ 1549556828
164 }
165 A = d(u.concat(j(z)), 512 + z.length * 8);
166 return p(d(x.concat(A), 512 + 128))
167 }
168 function t(w) {
169 var z = "0123456789abcdef",
170 v = "",
171 u, y;
172 for (y = 0; y < w.length; y += 1) {
173 u = w.charCodeAt(y);
174 v += z.charAt((u >>> 4) & 15) + z.charAt(u & 15)
175 }
176 return v
177 }
178 function m(u) {
179 return unescape(encodeURIComponent(u))
180 }
181 function q(u) {
182 return k(m(u))
183 }
184 function l(u) {
185 return t(q(u))
186 }
187 function h(u, v) {
188 return e(m(u), m(v))
189 }
190 function r(u, v) {
191 return t(h(u, v))
192 }
193 function f(v, w, u) {
194 if (!w) {
195 if (!u) {
196 return l(v)
197 }
198 return q(v)
199 }
200 if (!u) {
201 return r(w, v)
202 }
203 return h(w, v)
204 }
205 if (typeof define === "function" && define.amd) {
206 define(function() {
207 return f
208 })
209 } else {
210 g.md5 = f
211 }
212 } (this));
213
214 function md5(source) {
215 function safe_add(x, y) {
216 var lsw = (x & 65535) + (y & 65535),
217 msw = (x >> 16) + (y >> 16) + (lsw >> 16);
218 return msw << 16 | lsw & 65535
219 }
220 function bit_rol(num, cnt) {
221 return num << cnt | num >>> 32 - cnt
222 }
223 function md5_cmn(q, a, b, x, s, t) {
224 return safe_add(bit_rol(safe_add(safe_add(a, q), safe_add(x, t)), s), b)
225 }
226 function md5_ff(a, b, c, d, x, s, t) {
227 return md5_cmn(b & c | ~b & d, a, b, x, s, t)
228 }
229 function md5_gg(a, b, c, d, x, s, t) {
230 return md5_cmn(b & d | c & ~d, a, b, x, s, t)
231 }
232 function md5_hh(a, b, c, d, x, s, t) {
233 return md5_cmn(b ^ c ^ d, a, b, x, s, t)
234 }
235 function md5_ii(a, b, c, d, x, s, t) {
236 return md5_cmn(c ^ (b | ~d), a, b, x, s, t)
237 }
238 function binl_md5(x, len) {
239 x[len >> 5] |= 128 << len % 32;
240 x[(len + 64 >>> 9 << 4) + 14] = len;
241 var i, olda, oldb, oldc, oldd, a = 1732584193,
242 b = -271733879,
243 c = -1732584194,
244 d = 271733878;
245 for (i = 0; i < x.length; i += 16) {
246 olda = a;
247 oldb = b;
248 oldc = c;
249 oldd = d;
250 a = md5_ff(a, b, c, d, x[i], 7, -680876936);
251 d = md5_ff(d, a, b, c, x[i + 1], 12, -389564586);
252 c = md5_ff(c, d, a, b, x[i + 2], 17, 606105819);
253 b = md5_ff(b, c, d, a, x[i + 3], 22, -1044525330);
254 a = md5_ff(a, b, c, d, x[i + 4], 7, -176418897);
255 d = md5_ff(d, a, b, c, x[i + 5], 12, 1200080426);
256 c = md5_ff(c, d, a, b, x[i + 6], 17, -1473231341);
257 b = md5_ff(b, c, d, a, x[i + 7], 22, -45705983);
258 a = md5_ff(a, b, c, d, x[i + 8], 7, 1770035416);
259 d = md5_ff(d, a, b, c, x[i + 9], 12, -1958414417);
260 c = md5_ff(c, d, a, b, x[i + 10], 17, -42063);
261 b = md5_ff(b, c, d, a, x[i + 11], 22, -1990404162);
262 a = md5_ff(a, b, c, d, x[i + 12], 7, 1804603682);
263 d = md5_ff(d, a, b, c, x[i + 13], 12, -40341101);
264 c = md5_ff(c, d, a, b, x[i + 14], 17, -1502002290);
265 b = md5_ff(b, c, d, a, x[i + 15], 22, 1236535329);
266 a = md5_gg(a, b, c, d, x[i + 1], 5, -165796510);
267 d = md5_gg(d, a, b, c, x[i + 6], 9, -1069501632);
268 c = md5_gg(c, d, a, b, x[i + 11], 14, 643717713);
269 b = md5_gg(b, c, d, a, x[i], 20, -373897302);
270 a = md5_gg(a, b, c, d, x[i + 5], 5, -701558691);
271 d = md5_gg(d, a, b, c, x[i + 10], 9, 38016083);
272 c = md5_gg(c, d, a, b, x[i + 15], 14, -660478335);
273 b = md5_gg(b, c, d, a, x[i + 4], 20, -405537848);
274 a = md5_gg(a, b, c, d, x[i + 9], 5, 568446438);
275 d = md5_gg(d, a, b, c, x[i + 14], 9, -1019803690);
276 c = md5_gg(c, d, a, b, x[i + 3], 14, -187363961);
277 b = md5_gg(b, c, d, a, x[i + 8], 20, 1163531501);
278 a = md5_gg(a, b, c, d, x[i + 13], 5, -1444681467);
279 d = md5_gg(d, a, b, c, x[i + 2], 9, -51403784);
280 c = md5_gg(c, d, a, b, x[i + 7], 14, 1735328473);
281 b = md5_gg(b, c, d, a, x[i + 12], 20, -1926607734);
282 a = md5_hh(a, b, c, d, x[i + 5], 4, -378558);
283 d = md5_hh(d, a, b, c, x[i + 8], 11, -2022574463);
284 c = md5_hh(c, d, a, b, x[i + 11], 16, 1839030562);
285 b = md5_hh(b, c, d, a, x[i + 14], 23, -35309556);
286 a = md5_hh(a, b, c, d, x[i + 1], 4, -1530992060);
287 d = md5_hh(d, a, b, c, x[i + 4], 11, 1272893353);
288 c = md5_hh(c, d, a, b, x[i + 7], 16, -155497632);
289 b = md5_hh(b, c, d, a, x[i + 10], 23, -1094730640);
290 a = md5_hh(a, b, c, d, x[i + 13], 4, 681279174);
291 d = md5_hh(d, a, b, c, x[i], 11, -358537222);
292 c = md5_hh(c, d, a, b, x[i + 3], 16, -722521979);
293 b = md5_hh(b, c, d, a, x[i + 6], 23, 76029189);
294 a = md5_hh(a, b, c, d, x[i + 9], 4, -640364487);
295 d = md5_hh(d, a, b, c, x[i + 12], 11, -421815835);
296 c = md5_hh(c, d, a, b, x[i + 15], 16, 530742520);
297 b = md5_hh(b, c, d, a, x[i + 2], 23, -995338651);
298 a = md5_ii(a, b, c, d, x[i], 6, -198630844);
299 d = md5_ii(d, a, b, c, x[i + 7], 10, 1126891415);
300 c = md5_ii(c, d, a, b, x[i + 14], 15, -1416354905);
301 b = md5_ii(b, c, d, a, x[i + 5], 21, -57434055);
302 a = md5_ii(a, b, c, d, x[i + 12], 6, 1700485571);
303 d = md5_ii(d, a, b, c, x[i + 3], 10, -1894986606);
304 c = md5_ii(c, d, a, b, x[i + 10], 15, -1051523);
305 b = md5_ii(b, c, d, a, x[i + 1], 21, -2054922799);
306 a = md5_ii(a, b, c, d, x[i + 8], 6, 1873313359);
307 d = md5_ii(d, a, b, c, x[i + 15], 10, -30611744);
308 c = md5_ii(c, d, a, b, x[i + 6], 15, -1560198380);
309 b = md5_ii(b, c, d, a, x[i + 13], 21, 1309151649);
310 a = md5_ii(a, b, c, d, x[i + 4], 6, -145523070);
311 d = md5_ii(d, a, b, c, x[i + 11], 10, -1120210379);
312 c = md5_ii(c, d, a, b, x[i + 2], 15, 718787259);
313 b = md5_ii(b, c, d, a, x[i + 9], 21, -343485551);
314 a = safe_add(a, olda);
315 b = safe_add(b, oldb);
316 c = safe_add(c, oldc);
317 d = safe_add(d, oldd)
318 }
319 return [a, b, c, d]
320 }
321 function binl2rstr(input) {
322 var i, output = "";
323 for (i = 0; i < input.length * 32; i += 8) output += String.fromCharCode(input[i >> 5] >>> i % 32 & 255);
324 return output
325 }
326 function rstr2binl(input) {
327 var i, output = [];
328 output[(input.length >> 2) - 1] = undefined;
329 for (i = 0; i < output.length; i += 1) output[i] = 0;
330 for (i = 0; i < input.length * 8; i += 8) output[i >> 5] |= (input.charCodeAt(i / 8) & 255) << i % 32;
331 return output
332 }
333 function rstr_md5(s) {
334 return binl2rstr(binl_md5(rstr2binl(s), s.length * 8))
335 }
336 function rstr_hmac_md5(key, data) {
337 var i, bkey = rstr2binl(key),
338 ipad = [],
339 opad = [],
340 hash;
341 ipad[15] = opad[15] = undefined;
342 if (bkey.length > 16) bkey = binl_md5(bkey, key.length * 8);
343 for (i = 0; i < 16; i += 1) {
344 ipad[i] = bkey[i] ^ 909522486;
345 opad[i] = bkey[i] ^ 1549556828
346 }
347 hash = binl_md5(ipad.concat(rstr2binl(data)), 512 + data.length * 8);
348 return binl2rstr(binl_md5(opad.concat(hash), 512 + 128))
349 }
350 function rstr2hex(input) {
351 var hex_tab = "0123456789abcdef",
352 output = "",
353 x, i;
354 for (i = 0; i < input.length; i += 1) {
355 x = input.charCodeAt(i);
356 output += hex_tab.charAt(x >>> 4 & 15) + hex_tab.charAt(x & 15)
357 }
358 return output
359 }
360 function str2rstr_utf8(input) {
361 return unescape(encodeURIComponent(input))
362 }
363 function raw_md5(s) {
364 return rstr_md5(str2rstr_utf8(s))
365 }
366 function hex_md5(s) {
367 return rstr2hex(raw_md5(s))
368 }
369 function raw_hmac_md5(k, d) {
370 return rstr_hmac_md5(str2rstr_utf8(k), str2rstr_utf8(d))
371 }
372 function hex_hmac_md5(k, d) {
373 return rstr2hex(raw_hmac_md5(k, d))
374 }
375 return hex_md5(source)
376 }
377
378 function OOXX(m, r, d) {
379 var e = "DECODE";
380 var r = r ? r: "";
381 var d = d ? d: 0;
382 var q = 4;
383 r = md5(r);
384 var o = md5(r.substr(0, 16));
385 var n = md5(r.substr(16, 16));
386 if (q) {
387 if (e == "DECODE") {
388 var l = m.substr(0, q)
389 }
390 } else {
391 var l = ""
392 }
393 var c = o + md5(o + l);
394 var k;
395 if (e == "DECODE") {
396 m = m.substr(q);
397 k = base64_decode(m)
398 }
399 var h = new Array(256);
400 for (var g = 0; g < 256; g++) {
401 h[g] = g
402 }
403 var b = new Array();
404 for (var g = 0; g < 256; g++) {
405 b[g] = c.charCodeAt(g % c.length)
406 }
407 for (var f = g = 0; g < 256; g++) {
408 f = (f + h[g] + b[g]) % 256;
409 tmp = h[g];
410 h[g] = h[f];
411 h[f] = tmp
412 }
413 var t = "";
414 k = k.split("");
415 for (var p = f = g = 0; g < k.length; g++) {
416 p = (p + 1) % 256;
417 f = (f + h[p]) % 256;
418 tmp = h[p];
419 h[p] = h[f];
420 h[f] = tmp;
421 t += chr(ord(k[g]) ^ (h[(h[p] + h[f]) % 256]))
422 }
423 if (e == "DECODE") {
424 if ((t.substr(0, 10) == 0 || t.substr(0, 10) - time() > 0) && t.substr(10, 16) == md5(t.substr(26) + n).substr(0, 16)) {
425 t = t.substr(26)
426 } else {
427 t = ""
428 }
429 }
430 return t
431 };
View Code
(2)通过Python的selenium调用Chrome的无头浏览器(说明:低版本的Python可以用Phantomjs无头浏览器,Python3.6是直接弃用了这个浏览器,只好选择Chrome)
用Chrome无头浏览器需要Chrome60以上版本,根据Chrome版本下载对应(下图对面关系)的chromedrive.exe(说是好像Chrome60以上版本自带无头浏览器功能,楼主没有成功实现,还是老老实实下载了chromedriver,下载地址:http://chromedriver.storage.googleapis.com/index.html)
1 from urllib import request
2 import re
3 from selenium import webdriver
4 import requests
5
6
7 def get_html(url):
8 req = request.Request(url)
9 return request.urlopen(req).read()
10
11
12 def get_html2(url):
13 headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 '
14 '(KHTML, like Gecko)Chrome/62.0.3202.94 Safari/537.36'}
15 return requests.get(url, headers=headers).text
16
17
18 # 用chrome headless打开网页
19 def get_html3(url):
20 chromedriver = "C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe"
21 options = webdriver.ChromeOptions()
22 options.add_argument('--headless')
23 browser = webdriver.Chrome(chromedriver, chrome_options=options)
24 browser.get(url)
25 html = browser.page_source
26 browser.quit()
27 return html
28
29
30 # 打开网页返回网页内容
31 def open_webpage(html):
32 reg = r"(http:\S+(\.jpg|\.png|\.gif))"
33 imgre = re.compile(reg)
34 imglist = re.findall(imgre, html)
35 return imglist
36
37
38 if __name__ == '__main__':
39 url = "http://jandan.net/ooxx/page-2#comments"
40 html = get_html3(url)
41 reg = r"(http:\S+(\.jpg|\.png))"
42 imglist = re.findall(reg, html)
43 for img in imglist:
44 print(img[0])
3. 下载图片 用上面提到过的urllib.request.Request方法就可以实现
4. 测试都通过了,下面是汇总的完整源码OOXX_spider.py
1 from selenium import webdriver
2 import os
3 import requests
4 import re
5 from urllib.request import urlopen
6
7
8 # 全局声明的可以写到配置文件,这里为了读者方便看,故只写在一个文件里面
9 # 图片地址
10 picpath = r'E:\Python_Doc\Images'
11 # 网站地址
12 ooxx_url = "http://jandan.net/ooxx/page-{}#comments"
13 # chromedriver地址
14 chromedriver = "C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe"
15
16
17 # 保存路径的文件夹,没有则自己创建,不能创建目录
18 def setpath(name):
19 path = os.path.join(picpath, name)
20 if not os.path.isdir(path):
21 os.mkdir(path)
22 return path
23
24
25 # 用chrome headless打开网页
26 def gethtml(url):
27 options = webdriver.ChromeOptions()
28 options.add_argument('--headless')
29 browser = webdriver.Chrome(chromedriver, chrome_options=options)
30 browser.get(url)
31 html = browser.page_source
32 browser.quit()
33 return html
34
35
36 # 打开网页返回网页内容
37 def open_webpage(html):
38 reg = r"(http:\S+(\.jpg|\.png))"
39 imgre = re.compile(reg)
40 imglist = re.findall(imgre, html)
41 return imglist
42
43
44 # 保存照片
45 def savegirl(path, url):
46 content = urlopen(url).read()
47 with open(path + '/' + url[-11:], 'wb') as code:
48 code.write(content)
49
50
51 def do_task(path, index):
52 print("正在抓取低 %s 页" % index)
53 web_url = ooxx_url.format(index)
54 htmltext = gethtml(web_url)
55 imglists = open_webpage(htmltext)
56 print("抓取成功,开始保存 %s 页图片" % index)
57 for j in range(len(imglists)):
58 savegirl(path, imglists[j][0])
59
60
61 if __name__ == '__main__':
62 filename = "OOXX"
63 filepath = setpath(filename)
64 for i in range(1, 310):
65 do_task(filepath, i)
View Code
5. 分析:用调用chrome方法速度会比较慢,不过这个方法会是反爬虫技术越来越先进的必然选择,如何提速才是要考虑的关键
五、其他直接贴完整代码(难度:❤❤)
1. 网址:http://pic.yesky.com yesky_spider.py
1 from urllib import request
2 import re
3 import os
4 from bs4 import BeautifulSoup
5 from urllib.error import HTTPError
6
7
8 # 全局声明的可以写到配置文件,这里为了读者方便看,故只写在一个文件里面
9 # 图片地址
10 picpath = r'E:\Python_Doc\Images'
11 # 网站地址
12 mm_url = "http://pic.yesky.com/c/6_20771_%s.shtml"
13
14
15 # 保存路径的文件夹,没有则自己创建文件夹,不能创建上级文件夹
16 def setpath(name):
17 path = os.path.join(picpath, name)
18 if not os.path.isdir(path):
19 os.mkdir(path)
20 return path
21
22
23 # 获取html内容
24 def get_html(url):
25 req = request.Request(url)
26 return request.urlopen(req).read()
27
28
29 # 保存图片
30 def save_image(path, url):
31 req = request.Request(url)
32 get_img = request.urlopen(req).read()
33 with open(path + '/' + url[-14:] + '.jpg', 'wb') as fp:
34 fp.write(get_img)
35 return
36
37
38 def do_task(path, url):
39 html = get_html(url)
40 p = r'(http://pic.yesky.com/\d+/\d+.shtml)'
41 urllist = re.findall(p, str(html))
42 print(urllist)
43 for ur in urllist:
44 for i in range(2, 100):
45 url1 = ur[:-6] + "_" + str(i) + ".shtml"
46 print(url1)
47 try:
48 html1 = get_html(url1)
49 data = BeautifulSoup(html1, "lxml")
50 p = r"http://dynamic-image\.yesky\.com/740x-/uploadImages/\S+\.jpg"
51 image_list = re.findall(p, str(data))
52 print(image_list[0])
53 save_image(path, image_list[0])
54 except:
55 break
56
57
58 if __name__ == '__main__':
59
60 # 文件名
61 filename = "YeSky"
62 filepath = setpath(filename)
63
64 for i in range(2, 100):
65 print("正在6_20771_%s " % i)
66 url = mm_url % i
67 do_task(filepath, url)
View Code
2. 网站:http://www.7160.com 7160_spider
1 from urllib import request
2 import re
3 import os
4
5
6 # 全局声明的可以写到配置文件,这里为了读者方便看,故只写在一个文件里面
7 # 图片地址
8 picpath = r'E:\Python_Doc\Images'
9 # 7160地址
10 mm_url = "http://www.7160.com/xingganmeinv/list_3_%s.html"
11 mm_url2 = "http://www.7160.com/meinv/%s/index_%s.html"
12
13
14 # 保存路径的文件夹,没有则自己创建文件夹,不能创建上级文件夹
15 def setpath(name):
16 path = os.path.join(picpath, name)
17 if not os.path.isdir(path):
18 os.mkdir(path)
19 return path
20
21
22 def get_html(url):
23 req = request.Request(url)
24 return request.urlopen(req).read()
25
26
27 def get_image(path, url):
28 req = request.Request(url)
29 get_img = request.urlopen(req).read()
30 with open(path + '/' + url[-14:] + '.jpg', 'wb') as fp:
31 fp.write(get_img)
32 return
33
34
35 def do_task(path, url):
36 html = get_html(url)
37 p = r"<a href=\"/meinv/(\d+)/\""
38 get_list = re.findall(p, str(html))
39 for list in get_list:
40 for i in range(2, 200):
41 try:
42 url2 = mm_url2 % (list, i)
43 html2 = get_html(url2)
44 p = r"http://img\.7160\.com/uploads/allimg/\d+/\S+\.jpg"
45 image_list = re.findall(p, str(html2))
46 # print(image_list[0])
47 get_image(path, image_list[0])
48 except:
49 break
50 break
51
52
53 if __name__ == '__main__':
54 # 文件名
55 filename = "7160"
56 filepath = setpath(filename)
57
58 for i in range(2, 288):
59 print("正在下载页数:List_3_%s " % i)
60 url = mm_url % i
61 do_task(filepath, url)
View Code
3. 网站:http://www.263dm.com 263dm_spider.py
1 from urllib.request import urlopen
2 import urllib.request
3 import os
4 import sys
5 import time
6 import re
7 import requests
8
9
10 # 全局声明的可以写到配置文件,这里为了读者方便看,故只写在一个文件里面
11 # 图片地址
12 picpath = r'E:\Python_Doc\Images'
13 # 网站地址
14 mm_url = "http://www.263dm.com/html/ai/%s.html"
15
16
17 # 保存路径的文件夹,没有则自己创建文件夹,不能创建上级文件夹
18 def setpath(name):
19 path = os.path.join(picpath, name)
20 if not os.path.isdir(path):
21 os.mkdir(path)
22 return path
23
24
25 def getUrl(url):
26 aa = urllib.request.Request(url)
27 html = urllib.request.urlopen(aa).read()
28 p = r"(http://www\S*/\d{4}\.html)"
29 return re.findall(p, str(html))
30
31
32 def get_image(savepath, url):
33 aa = urllib.request.Request(url)
34 html = urllib.request.urlopen(aa).read()
35 p = r"(http:\S+\.jpg)"
36 url_list = re.findall(p, str(html))
37 for ur in url_list:
38 save_image(ur, ur, savepath)
39
40
41 def save_image(url_ref, url, path):
42 headers = {"Referer": url_ref,
43 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 '
44 '(KHTML, like Gecko)Chrome/62.0.3202.94 Safari/537.36'}
45 content = requests.get(url, headers=headers)
46 if content.status_code == 200:
47 with open(path + "/" + str(time.time()) + '.jpg', 'wb') as f:
48 for chunk in content:
49 f.write(chunk)
50
51
52 def do_task(savepath, index):
53 print("正在保存页数:%s " % index)
54 url = mm_url % i
55 get_image(savepath, url)
56
57
58 if __name__ == '__main__':
59 # 文件名
60 filename = "Adult"
61 filepath = setpath(filename)
62
63 for i in range(10705, 9424, -1):
64 do_task(filepath, i)
View Code
六、总结和补充
1. 获取网页内容有三种方式
urllib.request.Request和urllib.request.urlopen
——速度快,很容易被发现,不能获取js执行后的网页内容
requests带headers的请求方法
——速度快,可以实现伪装,不能获取js执行后的网页内容
chrome headless方法
——速度慢,等于浏览器访问,可以获取js执行后的网页内容