2020.5.30 commit🎉

Author: mochazi

README.md

@@ -1,17 +1,19 @@
 # **Python3Webcrawler**
-## **[哔哩哔哩作者：-相依-](https://space.bilibili.com/343154012)**   **UPDATE 2020 4 27**
+## **[哔哩哔哩作者：-相依-](https://space.bilibili.com/343154012)**   **UPDATE 2020 5 30**
 > **精心挑选了几个爬虫，给大家在学Scrapy框架之前打基础。**
 >> **该项目仅限学习交流，请勿用于商业用途，如有侵权，请联系删除。**
 
 |**程序依赖**|**安装指令**|**项目使用版本**|
 |:----:|:--------:|:--------:|
 |**lxml**|**pip install lxml**|**4.5.0**|
-|**requests**|**pip install requests**|**2.23.0**|
 |**aiohttp**|**pip install aiohttp**|**3.6.2**|
+|**requests**|**pip install requests**|**2.23.0**|
+|**PyExecJS**|**pip install PyExecJS**|**1.5.1**|
 |**sqlalchemy**|**pip install sqlalchemy**|**1.3.16**|
 |**beautifulsoup4**|**pip install beautifulsoup4**|**4.9.0**|
 
  * ### **京东   [官网地址](https://item.jd.com)** 
+ * ### **网易   [官网地址](https://www.163.com/)** 
  * ### **房天下  [官网地址](https://www.fang.com)** 
  * ### **快代理  [官网地址](https://www.kuaidaili.com)** 
  * ### **QQ音乐   [官网地址](https://y.qq.com)** 

破解有道翻译/crawl.py

@@ -0,0 +1,52 @@
+#Python3.7 
+#encoding = utf-8
+
+import time, math,random,hashlib
+import requests
+
+def get_html(name):
+
+    url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
+
+
+    ts = math.floor(time.time() * 1000)
+    salt = ts + int(random.random() * 10)
+
+    sign = hashlib.md5(("fanyideskweb" + name + str(salt) +"Nw(nmmbP%A-r6U3EUn]Aj").encode('utf-8')).hexdigest()
+    bv = hashlib.md5(("5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36").encode('utf-8')).hexdigest()
+
+    data = {
+        'i': name,
+        'from': 'AUTO',
+        'to': 'AUTO',
+        'smartresult': 'dict',
+        'client': 'fanyideskweb',
+        'salt': salt,
+        'sign': sign,
+        'ts': ts,
+        'bv': bv,
+        'doctype': 'json',
+        'version': '2.1',
+        'keyfrom': 'fanyi.web',
+        'action': 'FY_BY_CLICKBUTTION',
+    }
+
+    headers = {
+        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36',
+        'Referer': 'http://fanyi.youdao.com/',
+        #参考链接:http://fanyi.youdao.com/
+        #请在此处填写你的 Cookie
+    }
+
+
+    html = requests.post(url, headers=headers, data=data)#有需要的可以改成session写法
+    # print(html.json())
+    print('正在执行有道翻译程序:')
+    print('翻译的词:{}'.format(html.json()['translateResult'][0][0]['src']))
+    print('翻译结果:{}'.format(html.json()['translateResult'][0][0]['tgt']))
+
+if __name__ == "__main__":
+    
+    name = '靓仔'
+    
+    get_html(name)

破解网易登录/crawl.py

@@ -0,0 +1,91 @@
+#Python3.7 
+#encoding = utf-8
+
+import execjs,requests,time
+
+class User():#获取用户密码加密
+
+    def __init__(self,user_id,user_password):
+
+        self.user_id = user_id
+        self.user_password = user_password
+        self.session = requests.session()
+        self.session.headers = {
+            'Referer':'https://dl.reg.163.com/webzj/v1.0.1/pub/index_dl2_new.html?cd=https%3A%2F%2Ftemp.163.com%2Fspecial%2F00804C4H%2F&cf=urs_style_2019.css%3Ft%3D20190527&MGID=1590637061742.5342&wdaId=&pkid=MODXOXd&product=163',
+            'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36',
+            #请在此处输入你的Cookie
+            #参考链接 https://www.163.com/
+        }
+
+    def get_pw(self):
+
+        with open('pw.js','r',encoding='utf-8') as f:
+            content = f.read()
+      
+        js_data = execjs.compile(content)#编译js
+        pw = js_data.call('get_pw',self.user_password)#调用get_pw函数
+        return pw
+
+    def get_rtid(self):
+
+        with open('rtid.js','r',encoding='utf-8') as f:
+            content = f.read()
+   
+        js_data = execjs.compile(content)#编译js
+        rtid = js_data.call('get_rtid')#调用get_rtid函数
+        return rtid
+
+    def get_tk(self,rtid):
+
+        url = 'https://dl.reg.163.com/dl/gt'
+
+        params = {
+            'un':self.user_id,
+            'pkid':'MODXOXd',
+            'pd':'163',
+            'channel':'0',
+            'topURL':'https://www.163.com/',
+            'rtid':rtid,
+            'nocache':int(time.time()*1000),
+        }
+
+        html = self.session.get(url,params = params).json()
+        return html['tk']
+
+    def get_login(self,pw,rtid,tk):
+
+        url = 'https://dl.reg.163.com/dl/l'
+
+
+        data = {
+            'channel':'0',
+            'd':'10',
+            'domains':"163.com",
+            'l':'0',
+            'pd':"163",
+            'pkid':"MODXOXd",
+            'pw':pw,
+            'pwdKeyUp':'1',
+            'rtid':rtid,
+            't':int(time.time()*1000),
+            'tk':tk,
+            'topURL':"https://www.163.com/",
+            'un':self.user_id,
+        }
+
+        html = self.session.post(url,json = data).json()#传递JSON
+        return html
+
+
+if __name__ == "__main__":
+    
+    user = User('请输入你的账号','请输入你的密码')
+    pw = user.get_pw()#获取pw
+    rtid = user.get_rtid()#获取rtid
+
+    tk = user.get_tk(rtid)#获取tk
+
+    login = user.get_login(pw,rtid,tk)
+    print(login)
+
+