= 6) return;
215 | //console.log("旧代码111", pPath.toString());
216 | pPath.replaceWith(types.valueToNode(rightNode.value));
217 | modificationNum += 1
218 | //console.log("新代码111", pPath.toString())
219 | //console.log("-------------------")
220 | } else if (rightNode.type === "FunctionExpression") {
221 | // 此时这里的pPath.node为_0xa7a3b2["JHTcH"] 还要上一级才会有arguments的东西
222 | node = pPath.parentPath.node;
223 | let {parentPath} = pPath
224 | if (node.type !== "CallExpression") return;
225 | if (!rightNode.body || !rightNode.body.body) return;
226 | let bodyResult = rightNode.body.body[0];
227 | if (bodyResult.type !== "ReturnStatement") return;
228 | let {arguments} = node;
229 | //BinaryExpression 就是长这样的代码 return _0x398914 == _0x5433f6;
230 | if (bodyResult.argument.type === "BinaryExpression") {
231 | let {operator} = bodyResult.argument
232 | // 只有一个参数，说明是判断类型的，右边固定
233 | if (arguments.length === 1) {
234 | parentPath.replaceWith(types.binaryExpression(operator, node.arguments[0], bodyResult.argument.right))
235 | modificationNum += 1
236 | } else if (arguments.length === 2) {
237 | // console.log("旧代码222", pPath.toString())
238 | parentPath.replaceWith(types.binaryExpression(operator, node.arguments[0], node.arguments[1]))
239 | modificationNum += 1
240 | // console.log("新代码222", parentPath.toString())
241 | // console.log("-------------------")
242 |
243 | }
244 | } else if (bodyResult.argument.type === "CallExpression") {
245 | if (node.arguments.length >= 1) {
246 | // console.log("旧代码", pPath.parentPath.toString())
247 | pPath.parentPath.replaceWith(types.callExpression(node.arguments[0], node.arguments.slice(1)));
248 | modificationNum += 1
249 | // console.log("新代码", pPath.parentPath.toString())
250 | // console.log("-------------------")
251 | }
252 | } else if (bodyResult.argument.type === "LogicalExpression") {
253 | parentPath.replaceWith(types.logicalExpression("||", node.arguments[0], node.arguments[1]))
254 | modificationNum += 1
255 | }
256 | }
257 |
258 | }
259 | if (modificationNum === binding.referencePaths.length) {
260 | // console.log("删除了一个小数组。")
261 | path.remove()
262 | }
263 | }
264 | }
265 |
266 | // 获取动态post参数和加密的key
267 | let key_dict = [];
268 | let visitor3 = {
269 | "AssignmentExpression"(path) {
270 | let {node} = path;
271 | let {left, right} = node;
272 | if (!left.property || left.property.type !== "StringLiteral") return
273 | if (!right || !right.arguments || right.arguments.length !== 2) return;
274 | if (right.arguments[1].type !== "StringLiteral" || right.arguments[1].value.length !== 8) return;
275 | // console.log(left.property.value,right.arguments[1].value)
276 | key_dict.push([left.property.value, right.arguments[1].value])
277 | },
278 | // 获取最后三个参数及key
279 | "CallExpression"(path) {
280 | let {node} = path;
281 | if (!node.arguments || node.arguments.length !== 3) return; // 必须是三个参数 对象，参数名(2长度)，加密的值
282 | if (node.arguments[1].type !== "StringLiteral" || node.arguments[1].value.length !== 2) return;
283 | let key = node.arguments[1].value;
284 | let right_node = node.arguments[2];
285 | if (right_node.type != "CallExpression") return;
286 | if (right_node.arguments.length !== 2) return;
287 | if (right_node.arguments[1].value.length == 8) {
288 | let value = right_node.arguments[1].value;
289 | key_dict.push([key, value]);
290 | }
291 | }
292 |
293 | }
294 | traverse(ast, visitor1);
295 | traverse(ast, visitorArray);
296 | traverse(ast, visitor2);
297 | traverse(ast, visitor3);
298 | console.log(key_dict.length);
299 | console.log(key_dict);
300 |
301 | // let {code} = generator(ast, opts = {
302 | // compact: true,
303 | // jsescOption: {minified: true, retainFunctionParens: true, retainLines: true}
304 | // })
305 | // fs.writeFile('./demoNew.js', code, (err) => {
306 | // });
307 |
308 | console.timeEnd("耗时:")
309 |
--------------------------------------------------------------------------------
/数美滑块.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | """
3 | @Time ： 2022/3/7 18:00
4 | @Auth ： 黑脸怪
5 | @File ：index.py.py
6 |
7 | """
8 | import base64
9 | import json
10 | import random
11 | import time
12 | import urllib.parse
13 | import cv2
14 |
15 | from pyDes import des, ECB
16 | import numpy as np
17 | import requests
18 |
19 |
20 | class shumei:
21 | domain_url="https://castatic.fengkongcloud.cn/"
22 | bg_url=""
23 | fg_url=""
24 | rid=""
25 | bg=None
26 | fg=None
27 | def __init__(self):
28 | self.r=requests.session()
29 |
30 | def get_captcha(self,organization):
31 | url="https://captcha.fengkongcloud.cn/ca/v1/register"
32 | param={
33 | "rversion": "1.0.3",
34 | "sdkver": "1.1.3",
35 | "data": "{}",
36 | "callback": "sm_"+str(int(time.time()*1000)),
37 | "organization": organization,
38 | "model": "slide",
39 | "lang":"zh-cn",
40 | "appId": "default",
41 | "channel": "DEFAULT"
42 | }
43 | response=self.r.get(url,params=param)
44 | try:
45 | if response.status_code==200:
46 | sm_json=json.loads(response.text[17:-1])
47 | bg=sm_json["detail"]["bg"]
48 | fg=sm_json["detail"]["fg"]
49 | self.bg_url=urllib.parse.urljoin(self.domain_url,bg)
50 | self.fg_url=urllib.parse.urljoin(self.domain_url,fg)
51 | self.rid=sm_json["detail"]["rid"]
52 | # print(param,"params")
53 | # print(response.text,"请求")
54 |
55 | except:
56 | print(response.text)
57 | print("未知失败，自己验证")
58 |
59 | #访问背景前景页面
60 | def _visit_bg_fg(self):
61 | try:
62 | self.bg=self.r.get(self.bg_url).content
63 | self.fg=self.r.get(self.fg_url).content
64 | with open("a.png","wb") as f:
65 | f.write(self.r.get(self.bg_url).content)
66 | with open("b.png","wb") as f:
67 | f.write(self.r.get(self.fg_url).content)
68 |
69 | return True
70 | except:
71 | print("获取前景背景图片失败")
72 | return None
73 | def get_distance(self):
74 | if self._visit_bg_fg() is None:
75 | return
76 | # with open('a.png', 'rb') as f:
77 | # background_bytes = f.read()
78 | #
79 | # with open('b.png', 'rb') as f:
80 | # target_bytes = f.read()
81 | # res = det.slide_match(self.fg, self.bg)
82 | # # 获取的图片是600像素 但验证是300 所以除以二
83 | # print(res)
84 | # return int(res["target"][0])
85 |
86 | target = cv2.imdecode(np.asarray(bytearray(self.fg), dtype=np.uint8), 0)
87 | template = cv2.imdecode(np.asarray(bytearray(self.bg), dtype=np.uint8), 0)
88 | result = cv2.matchTemplate(target, template, cv2.TM_CCORR_NORMED)
89 | _, distance = np.unravel_index(result.argmax(), result.shape)
90 | return distance
91 |
92 | def pad(self,b):
93 | """
94 | 块填充
95 | """
96 | block_size = 8
97 | while len(b) % block_size:
98 | b += b'\0'
99 | return b
100 | def getEncryptContent(self,a, b):
101 | # js = execjs.compile(self.js_code)
102 | #
103 | # print(a,b,js.call("getEncryptContent", a, b))
104 | # return js.call("getEncryptContent", a, b)
105 | des_obj = des(b.encode(), mode=ECB)
106 | content = self.pad(str(a).replace(' ', '').encode())
107 | return base64.b64encode(des_obj.encrypt(content)).decode('utf-8')
108 |
109 | def get_trajectory(self,distance):
110 | ge = []
111 | y = 0
112 | v = 0
113 | t = 1
114 | current = 0
115 | mid = distance * 3 / 4
116 | exceed = 20
117 | z = t
118 |
119 | ge.append([0, 0, 1])
120 |
121 | while current < (distance + exceed):
122 | if current < mid / 2:
123 | a = 15
124 | elif current < mid:
125 | a = 20
126 | else:
127 | a = -30
128 | a /= 2
129 | v0 = v
130 | s = v0 * t + 0.5 * a * (t * t)
131 | current += int(s)
132 | v = v0 + a * t
133 |
134 | y += random.randint(-5, 5)
135 | z += 100 + random.randint(0, 10)
136 |
137 | ge.append([min(current, (distance + exceed)), y, z])
138 |
139 | while exceed > 0:
140 | exceed -= random.randint(0, 5)
141 | y += random.randint(-5, 5)
142 | z += 100 + random.randint(0, 10)
143 | ge.append([min(current, (distance + exceed)), y, z])
144 | # print(ge)
145 | return ge
146 |
147 | # return "{}".format(ge).replace(" ", ""), ge[-1][2]
148 | # return "{}".format(ge).replace(" ", "")
149 |
150 | def ok(self,tq,ub,zs,organization):
151 | url="https://captcha.fengkongcloud.cn/ca/v2/fverify"
152 | params={
153 | "sdkver": "1.1.3",
154 | "cn": "4gX7HfzFoIE=",
155 | "je": "J95iyFR+B34=",
156 | "rid": self.rid,
157 | "vm": "kRSb3H6Sr+M=",
158 | "zj": "YXtzSGH4Kx4=",
159 | "protocol": "148",
160 | "act.os": "web_pc",
161 | "tq": tq,
162 | "ox": "ixh0fmsqQqE=",
163 | "tb": "jbIXAuW9ClU=",
164 | "organization": organization,
165 | "fp": "ePjf+CsNviw=",
166 | "ub": ub,
167 | "rr": "yYCBEY0C7PQ=",
168 | "ostype": "web",
169 | "rversion": "1.0.3",
170 | "zs":zs,
171 | "callback": "sm_1646734280304"
172 | }
173 | res=self.r.get(url,params=params)
174 | print(res.text)
175 | if json.loads(res.text[17:-1])["riskLevel"]=="PASS":
176 | return True
177 |
178 | def main(self,organization="RlokQwRlVjUrTUlkIqOg"):
179 | self.get_captcha(organization)
180 | #distance距离
181 | distance = self.get_distance()
182 | print(distance,"距离")
183 | # tq加密的滑动距离
184 | tq=self.getEncryptContent(distance/600,"c78a7666")
185 | #ub滑动时间
186 | ub=self.getEncryptContent(random.randint(2001,4999),"eb994a6b")
187 | #zs滑动轨迹
188 | trajectory=self.get_trajectory(distance/2)
189 | # print(trajectory)
190 | zs=self.getEncryptContent(trajectory,"201cab4a")
191 | if self.ok(tq,ub,zs,organization):
192 | return self.rid
193 |
194 |
195 |
196 | sm=shumei()
197 | requestId=sm.main(organization="xQsKB7v2qSFLFxnvmjdO")
198 | if requestId is not None:
199 | print("滑块成功")
200 | # url="http://jpebook.ly.com/suppliersharing/Account/Login"
201 | # headers={
202 | # "Host": "jpebook.ly.com",
203 | # "Connection": "keep-alive",
204 | # "Accept": "application/json, text/plain, */*",
205 | # "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36",
206 | # "Content-Type": "application/json;charset=UTF-8",
207 | # "Origin": "http://jpebook.ly.com",
208 | # "Referer": "http://jpebook.ly.com/suppliersharing/Account/Login?ReturnUrl=%2Fsuppliersharing",
209 | # "Accept-Language": "zh-CN,zh;q=0.9"
210 | # }
211 | # data={"type":0,"loginName":"你是黑脸怪","password":"8ae252facf16cf0b0d8677bb3f889d33","checkPassword":"","validCode":"","codeResponse":requestId,"codeType":"sm"}
212 | # res=requests.post(url=url,json=data,headers=headers)
213 | # print(res.text)
214 | else:
215 | print("滑块失败，重来一次吧")
216 |
217 | # print(distance,get_random(distance))
218 |
219 |
--------------------------------------------------------------------------------
/豆瓣.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 |
3 | import re
4 | import time
5 | import pandas as pd
6 | import requests
7 | import logging
8 | import urllib.parse
9 | from lxml import etree
10 |
11 | """
12 | @Time ： 2022/2/23 13:48
13 | @Auth ： 黑脸怪
14 | @File ：pd.py
15 |
16 | """
17 |
18 | logging.basicConfig(
19 | level=logging.INFO,
20 | format='%(lineno)s行 时间:%(asctime)s 文件名:%(filename)s %(levelname)s: %(message)s',
21 | datefmt='%H:%M:%S',
22 | filename="./mylog.txt"
23 | )
24 |
25 | class douban():
26 | def __init__(self):
27 | self.num=0 #序号
28 | self.start_url=""
29 | self.old_url=[] #访问过的放这里 判断存在就不继续往下放了
30 | self.list_page=[] #所有详情页放这里
31 | self.next_page=[] #访问列表也后 把下一页存在这里
32 | self.err_page=[] #暂时失败的url存放在这 到时候重试
33 | self.result_list = []
34 | self.headers = {
35 | 'Connection': 'keep-alive',
36 | 'Cache-Control': 'max-age=0',
37 | 'Upgrade-Insecure-Requests': '1',
38 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36',
39 | 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
40 | 'Sec-Fetch-User': '?1',
41 | 'Sec-Fetch-Dest': 'document',
42 | 'Accept-Language': 'zh-CN,zh;q=0.9'
43 | }
44 |
45 | def main(self,url):
46 | #这里赋值是为了之后urljoin用
47 | self.start_url=url
48 | self.next_page.append(url)
49 | while len(self.next_page)>0:
50 | self.list_and_next()
51 | # print("list_page->>>>>>>",self.list_page)
52 | print("next_page->>>>>>>",self.next_page)
53 | time.sleep(2)
54 | while len(self.list_page)>0:
55 | url=self.list_page.pop()
56 | html=self.data_get(url)
57 | if html is not None:
58 | self.data_parse(html,url)
59 | time.sleep(2)
60 | if len(self.result_list)>0:
61 | self.save_to_xlsx("./豆瓣影评-{}.xlsx".format(str(int(time.time()))))
62 |
63 | #输入列表的网址 获取列表url和下一页url保存到self变量中
64 |
65 | def list_and_next(self):
66 | url=self.next_page.pop()
67 | try:
68 | response=requests.get(url,headers=self.headers,timeout=20)
69 | except Exception as e:
70 | logging.info("访问出错")
71 | print(e)
72 | return None
73 |
74 | if "评论" in response.text:
75 | html=etree.HTML(response.text)
76 | div_list=html.xpath('//*[@id="content"]/div/div[1]/div[1]/div//div/div/div[3]/a[3]/@href')
77 | if len(div_list) ==0:
78 | div_list=html.xpath('//*[@id="content"]/div/div[1]/div[1]/div[2]/div//div/div/div[3]/a[3]/@href')
79 |
80 | n_p = html.xpath('//*[@id="content"]/div/div[1]/div[2]/span[4]/a/@href')
81 | if len(n_p)==0:
82 | n_p=html.xpath('//*[@id="content"]/div/div[1]/div[2]/span[5]/a/@href')
83 |
84 | for l in div_list:
85 | if l not in self.old_url:
86 | self.list_page.insert(0,l)
87 |
88 | if len(n_p)>0:
89 | next_page=n_p[0]
90 | if next_page not in self.old_url:
91 | self.next_page.append(urllib.parse.urljoin(self.start_url,next_page))
92 | else:
93 | print("没有下一页了。")
94 |
95 | else:
96 | logging.info("其他错误，暂时没做解析,状态码："+str(response.status_code)+str(response.text))
97 |
98 | def data_get(self,url):
99 | res=requests.get(url,headers=self.headers,timeout=20)
100 | # logging.debug(url+"状态码："+str(res.status_code))
101 | try:
102 | if res.status_code==200:
103 | return res.text
104 | elif res.status_code==404:
105 | return None
106 | elif res.status_code==403:
107 | logging.info(url+"状态码："+str(res.status_code)+"可能没权限访问")
108 | logging.info(res.text)
109 | else:
110 | logging.info("失败，状态码："+str(res.status_code))
111 | self.err_page.append(url)
112 | return None
113 | except:
114 | self.err_page.append(url)
115 | def data_parse(self,html,url):
116 | html2 = etree.HTML(html)
117 | author = html2.xpath('//*[@class="main-hd"]/a/span/text()')
118 | star = html2.xpath('//*[@id="content"]/div/div[1]/div[1]/div/header/span[1]/@title')
119 | R_time = html2.xpath('//*[@id="content"]/div/div[1]/div[1]/div/header/span[3]/text()')
120 | Title = html2.xpath('//*[@id="content"]/div/div[1]/h1/span/text()')
121 | Topics = html2.xpath('//*[@id="content"]/div/div[1]/a/h2/text()')
122 | Spoiler = html2.xpath('//*[@class="main-bd"]/p[1]/text()')
123 | try:
124 | content = re.search('
(.+)
', html).group(0)
125 | content = content.replace('
", "")
127 | except:
128 | logging.debug("获取title失败")
129 | content="获取title失败"
130 | zan = html2.xpath('//*[@class="main-panel-useful"]/button[1]/text()')
131 | cai = html2.xpath('//*[@class="main-panel-useful"]/button[2]/text()')
132 | Resp = re.findall('\[\{\".+\"\}\]', html)
133 |
134 | result = []
135 | self.num+=1
136 | result.append(self.num)
137 | result.append(url)
138 | result.append(author[0]) if len(author) > 0 else result.append("")
139 | result.append(star[0]) if len(star) > 0 else result.append("")
140 | result.append(R_time[0]) if len(R_time) > 0 else result.append("")
141 | result.append(Title[0]) if len(Title) > 0 else result.append("")
142 | result.append(Topics[0]) if len(Topics) > 0 else result.append("")
143 | result.append(str(Spoiler[0]).strip()) if len(Spoiler) > 0 else result.append("")
144 | result.append(content)
145 | result.append(str(zan[0]).strip()) if len(zan) > 0 else result.append("")
146 | result.append(str(cai[0]).strip()) if len(cai) > 0 else result.append("")
147 | result.append(Resp[0]) if len(Resp) > 0 else result.append("")
148 | # print(result)
149 | logging.info(Title)
150 | self.result_list.append(result)
151 | def save_to_xlsx(self,filename):
152 | columns = ["序号","评论链接","发布者", "评分星级", "评论时间","标题","话题","是否可能有剧透","影评内容","有用数","没用数","回应"]
153 | dt = pd.DataFrame(self.result_list, columns=columns)
154 | dt.to_excel(filename,index=0)
155 | logging.info("完成~~~~")
156 |
157 |
158 | d=douban()
159 | d.main("https://movie.douban.com/subject/26752088/reviews?start=0")
160 |
--------------------------------------------------------------------------------