├── .gitattributes
├── README.md
├── .gitignore
├── Tc_AdjustV1.0.py
└── Tc_AdjustV2.0.py


/.gitattributes:
--------------------------------------------------------------------------------
1 | # Auto detect text files and perform LF normalization
2 | * text=auto
3 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Adjust_code
 2 | 基于python3.7.2
 3 | 
 4 | 4.10 更新
 5 | 两个网页源代码发生变化，爬不了了，现在有点懒不想维护..
 6 | 
 7 | 2月15日成绩出来后如果真的有调剂这方面的需求可以尝试一下此软件。
 8 | 
 9 | 研招网没爬是因为...
10 | 对调剂同学太不友好。
11 | 
12 | 求大佬指正不足之处！
13 | 2019.01.31  
14 | V2.0 
15 | 优化界面，使用内置tkinter进行设计
16 | 
17 | /***********************************************************
18 | 
19 | 2019.01.29
20 | V1.0 
21 | 使用正则表达式和xpath进行匹配信息，在黑框中能够定时查询。
22 | 有对爬虫感兴趣的同学可以一起学习~
23 | 
24 | 小木虫 http://muchong.com/bbs/kaoyan.php?action=adjust&type=1&page=1
25 | 
26 | 中国考研 http://www.chinakaoyan.com/tiaoji/schoollist/pagenum/1.shtml
27 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
  1 | # Byte-compiled / optimized / DLL files
  2 | __pycache__/
  3 | *.py[cod]
  4 | *$py.class
  5 | 
  6 | # C extensions
  7 | *.so
  8 | 
  9 | # Distribution / packaging
 10 | .Python
 11 | build/
 12 | develop-eggs/
 13 | dist/
 14 | downloads/
 15 | eggs/
 16 | .eggs/
 17 | lib/
 18 | lib64/
 19 | parts/
 20 | sdist/
 21 | var/
 22 | wheels/
 23 | *.egg-info/
 24 | .installed.cfg
 25 | *.egg
 26 | MANIFEST
 27 | 
 28 | # PyInstaller
 29 | #  Usually these files are written by a python script from a template
 30 | #  before PyInstaller builds the exe, so as to inject date/other infos into it.
 31 | *.manifest
 32 | *.spec
 33 | 
 34 | # Installer logs
 35 | pip-log.txt
 36 | pip-delete-this-directory.txt
 37 | 
 38 | # Unit test / coverage reports
 39 | htmlcov/
 40 | .tox/
 41 | .nox/
 42 | .coverage
 43 | .coverage.*
 44 | .cache
 45 | nosetests.xml
 46 | coverage.xml
 47 | *.cover
 48 | .hypothesis/
 49 | .pytest_cache/
 50 | 
 51 | # Translations
 52 | *.mo
 53 | *.pot
 54 | 
 55 | # Django stuff:
 56 | *.log
 57 | local_settings.py
 58 | db.sqlite3
 59 | 
 60 | # Flask stuff:
 61 | instance/
 62 | .webassets-cache
 63 | 
 64 | # Scrapy stuff:
 65 | .scrapy
 66 | 
 67 | # Sphinx documentation
 68 | docs/_build/
 69 | 
 70 | # PyBuilder
 71 | target/
 72 | 
 73 | # Jupyter Notebook
 74 | .ipynb_checkpoints
 75 | 
 76 | # IPython
 77 | profile_default/
 78 | ipython_config.py
 79 | 
 80 | # pyenv
 81 | .python-version
 82 | 
 83 | # celery beat schedule file
 84 | celerybeat-schedule
 85 | 
 86 | # SageMath parsed files
 87 | *.sage.py
 88 | 
 89 | # Environments
 90 | .env
 91 | .venv
 92 | env/
 93 | venv/
 94 | ENV/
 95 | env.bak/
 96 | venv.bak/
 97 | 
 98 | # Spyder project settings
 99 | .spyderproject
100 | .spyproject
101 | 
102 | # Rope project settings
103 | .ropeproject
104 | 
105 | # mkdocs documentation
106 | /site
107 | 
108 | # mypy
109 | .mypy_cache/
110 | .dmypy.json
111 | dmypy.json
112 | 
113 | # Pyre type checker
114 | .pyre/
115 | 


--------------------------------------------------------------------------------
/Tc_AdjustV1.0.py:
--------------------------------------------------------------------------------
  1 | import requests
  2 | import re
  3 | import time
  4 | from lxml import etree
  5 | search_profession = input("你要查找的专业或学校是：")
  6 | print("\n","Powered by Dong dong Xu")
  7 | print("\n","      更多代码均放在   -->Github : https://github.com/Tcloser")
  8 | print("\n")
  9 | print("写在前面：本程序用于实时爬取最新调剂信息，关键词可以根据所爬内容适当修改，1.0版本主要进行测试信息及界面优化。")
 10 | print("\n")
 11 | print("                                            调剂信息最新发表内容如下所示：")
 12 | # 中国考研网 http://www.chinakaoyan.com/tiaoji/schoollist/pagenum/1.shtml
 13 | chinakaoyan_index = 1
 14 | web_site_chinakaoyan   = 'http://www.chinakaoyan.com/tiaoji/schoollist/pagenum/'+str(chinakaoyan_index)+'.shtml'  #网址第一页 可用循环多次
 15 | school_sign_chinakaoyan = '<span class="school">(.*?)</span>'                             #标题特征
 16 | profession_sign_chinakaoyan = '<span class="name">(.*?)</span>'                          #专业特征
 17 | title_sign_chinakaoyan = 'target="_blank">(.*?)</a></span>'                               #发表标题
 18 | url_sign_chinakaoyan   = '<span class="title"><a href="(.*?)" ti'                        #链接特征
 19 | 
 20 | # 小木虫 http://muchong.com/bbs/kaoyan.php?&page=1
 21 | muchong_index = 1
 22 | title_sign_muchong = 'class="xmc_ft12">(.*?)</a>'                                        #标题特征
 23 | profession_sign_muchong = '//tbody[@class="forum_body_manage"]/tr/td[last()-2]/text()'   #xpath专业特征
 24 | url_sign_muchong   = 'lp20"><a href="(.*?)" tar'                                         #链接特征
 25 | time_sign_muchong =  '//tbody[@class="forum_body_manage"]/tr/td[last()]/text()'
 26 | 
 27 | class Spider(object):
 28 |     @staticmethod
 29 |     def start_request_chinakaoyan (websit1) :
 30 |         response = requests.get(websit1)
 31 |         res = response.text  # 将信息从前端代码拿出
 32 |         # 正则表达式
 33 |         question_school = re.findall(school_sign_chinakaoyan, res) #标题特征
 34 |         question_prof = re.findall(profession_sign_chinakaoyan, res)#专业特征
 35 |         question_url  = re.findall(url_sign_chinakaoyan, res)   #链接特征
 36 |         question_title = re.findall(title_sign_chinakaoyan, res)  # 标题特征
 37 |         del (question_school[0]) #chinakaoyan.com第一个信息删除
 38 |         del (question_prof[0])
 39 |         for quetitle, queprof, queurl  in zip(question_title, question_prof,question_url):  #列表显示标题与部分地址
 40 |             print(" *----------------------------------------------------------------------------------------------------*")
 41 |             print("      "+quetitle,queprof,"http://www.chinakaoyan.com/"+queurl)#打印出来
 42 |         return question_title,question_prof,question_url  #将问题名称与地址输出至list，url保存
 43 | 
 44 |     @staticmethod
 45 |     def start_request_muchong(websit2):
 46 |         response = requests.get(websit2)
 47 |         res = response.text  # 将信息从前端代码拿出
 48 |         html = etree.HTML(response.text)  # 将信息从前端代码拿出
 49 |         # 正则表达式
 50 |         question_list = re.findall(title_sign_muchong, res)  # 标题特征
 51 |         question_porf = html.xpath(profession_sign_muchong)  # 111111
 52 |         question_time = html.xpath(time_sign_muchong)
 53 |         question_url = re.findall(url_sign_muchong, res)  # 链接特征
 54 |         for quetime,quelist, queporf, queurl in zip(question_time,question_list, question_porf, question_url):  # 列表显示标题与部分地址
 55 |             print(
 56 |                 " *----------------------------------------------------------------------------------------------------*")
 57 |             print("      " + quetime,quelist, queporf, queurl)  # 打印出来
 58 |         return question_list,question_porf, question_url  # 将问题名称与地址输出至list，url保存
 59 | 
 60 |     @staticmethod
 61 |     def seach_keyword_chinakaoyan(question_list, question_url):
 62 |         number = 0
 63 |         sum_number = 0
 64 |         for i in question_list:
 65 |             if re.findall(search_profession, i) == [search_profession]:#匹配相同字段，对应链接顺序
 66 |                 print(i,"---请点击：","http://www.chinakaoyan.com"+question_url[number])
 67 |                 sum_number +=1
 68 |             number = number + 1
 69 |         if sum_number == 0:
 70 |             print("                      目前最新发布中没有搜索到相关内容。")
 71 | 
 72 |     @staticmethod
 73 |     def seach_keyword_muchong(question_list, question_url):
 74 |         number = 0
 75 |         sum_number = 0
 76 |         for i in question_list:
 77 |             if re.findall(search_profession, i) == [search_profession]:#匹配相同字段，对应链接顺序
 78 |                 print(i,"---请点击：",question_url[number])
 79 |                 sum_number +=1
 80 |             number = number + 1
 81 |         if sum_number == 0:
 82 |             print("                      目前最新发布中没有搜索到相关内容。")
 83 | 
 84 | spider = Spider()
 85 | while 1:#定时60s查询
 86 |     (title_chinakaoyan,prof_chinakaoyan, url_chinakaoyan) = spider.start_request_chinakaoyan(web_site_chinakaoyan)# 查询 chinakaoyan.com一页
 87 |     #print('                                                      第', str(chinakaoyan_index),'页内容')
 88 |     print("\n","小木虫网站信息如下：                      ","\n")
 89 |     # spider.seach_keyword(list,url)
 90 |     while 1: #小木虫三页
 91 |         if muchong_index != 4:
 92 |             web_site_muchong = 'http://muchong.com/bbs/kaoyan.php?action=adjust&type=1&page=' + str(muchong_index)
 93 |             (list_muchong, porf_muchong,url_muchong) = spider.start_request_muchong(web_site_muchong)  # 查询 muchong
 94 |             muchong_index = muchong_index + 1
 95 |         else :
 96 |             break
 97 |     print("\n")
 98 |     spider.seach_keyword_chinakaoyan(prof_chinakaoyan, url_chinakaoyan)#对chinakaoyan专业进行关键字查询
 99 |     spider.seach_keyword_chinakaoyan(title_chinakaoyan, url_chinakaoyan)#对chinakaoyan学校
100 |     print("\n")
101 |     spider.seach_keyword_muchong(porf_muchong, url_muchong)#对小木虫学校专业信息进行关键字匹配
102 |     spider.seach_keyword_muchong(list_muchong, url_muchong)#对小木虫学校信息进行关键字匹配
103 |     print("                                   ","1分钟后将对最新信息进行检索")
104 |     muchong_index = 1#小木虫页面复位
105 |     time.sleep(60)
106 | 
107 | 
108 | 
109 | 
110 | 
111 | 
112 | 
113 | 


--------------------------------------------------------------------------------
/Tc_AdjustV2.0.py:
--------------------------------------------------------------------------------
  1 | import requests
  2 | from lxml import etree
  3 | from tkinter import *
  4 | 
  5 | # print("\n","Powered by Dong dong Xu")
  6 | # print("\n","      更多代码均放在   -->Github : https://github.com/Tcloser")
  7 | # print("\n")
  8 | # print("写在前面：本程序用于实时爬取最新调剂信息，关键词可以根据所爬内容适当修改，1.0版本主要进行测试信息及界面优化。")
  9 | # print("\n")
 10 | # print("                                            调剂信息最新发表内容如下所示：")
 11 | # 中国考研网 http://www.chinakaoyan.com/tiaoji/schoollist/pagenum/1.shtml
 12 | chinakaoyan_index = 1
 13 | web_site_chinakaoyan   = 'http://www.chinakaoyan.com/tiaoji/schoollist/pagenum/'+str(chinakaoyan_index)+'.shtml'  #网址第一页 可用循环多次
 14 | school_sign_chinakaoyan = '<span class="school">(.*?)</span>'                             #标题特征
 15 | profession_sign_chinakaoyan = '<span class="name">(.*?)</span>'                          #专业特征
 16 | title_sign_chinakaoyan = 'target="_blank">(.*?)</a></span>'                               #发表标题
 17 | url_sign_chinakaoyan   = '<span class="title"><a href="(.*?)" ti'                        #链接特征
 18 | 
 19 | # 小木虫 http://muchong.com/bbs/kaoyan.php?&page=1
 20 | muchong_index = 1
 21 | title_sign_muchong = 'class="xmc_ft12">(.*?)</a>'                                        #标题特征
 22 | profession_sign_muchong = '//tbody[@class="forum_body_manage"]/tr/td[last()-2]/text()'   #xpath专业特征
 23 | url_sign_muchong   = 'lp20"><a href="(.*?)" tar'                                         #链接特征
 24 | time_sign_muchong =  '//tbody[@class="forum_body_manage"]/tr/td[last()]/text()'
 25 | 
 26 | 
 27 | class Spider(object):
 28 |     @staticmethod
 29 |     def start_request_chinakaoyan (websit1) :
 30 |         response = requests.get(websit1)
 31 |         res = response.text  # 将信息从前端代码拿出
 32 |         # 正则表达式
 33 |         question_school = re.findall(school_sign_chinakaoyan, res) #标题特征
 34 |         question_prof = re.findall(profession_sign_chinakaoyan, res)#专业特征
 35 |         question_url  = re.findall(url_sign_chinakaoyan, res)   #链接特征
 36 |         question_title = re.findall(title_sign_chinakaoyan, res)  # 标题特征
 37 |         del (question_school[0]) #chinakaoyan.com第一个信息删除
 38 |         del (question_prof[0])
 39 |         for quetitle, queprof, queurl  in zip(question_title, question_prof,question_url):  #列表显示标题与部分地址
 40 |             #print(" *----------------------------------------------------------------------------------------------------*")
 41 |             #print("      "+quetitle,queprof,"http://www.chinakaoyan.com/"+queurl)#打印出来
 42 |             #text1.delete(0.0, END)
 43 |             text1.insert('insert',quetitle,queprof,"     http://www.chinakaoyan.com/"+queurl+"\n"+"\n")
 44 |         return question_title,question_prof,question_url  #将问题名称与地址输出至list，url保存
 45 | 
 46 |     @staticmethod
 47 |     def start_request_muchong(websit2):
 48 |         response = requests.get(websit2)
 49 |         res = response.text  # 将信息从前端代码拿出
 50 |         html = etree.HTML(response.text)  # 将信息从前端代码拿出
 51 |         # 正则表达式
 52 |         question_list = re.findall(title_sign_muchong, res)  # 标题特征
 53 |         question_porf = html.xpath(profession_sign_muchong)  # 111111
 54 |         question_time = html.xpath(time_sign_muchong)
 55 |         question_url = re.findall(url_sign_muchong, res)  # 链接特征
 56 |         for quetime,quelist, queporf, queurl in zip(question_time,question_list, question_porf, question_url):  # 列表显示标题与部分地址
 57 |             #print(" *----------------------------------------------------------------------------------------------------*")
 58 |             #print("      " + quetime,quelist, queporf, queurl)  # 打印出来
 59 |             text1.insert('insert', quetime+str(quelist)+queporf+queurl +"\n"+"\n")
 60 |             #text1.insert(quetime,quelist, queporf, queurl)
 61 |         return question_list,question_porf, question_url  # 将问题名称与地址输出至list，url保存
 62 | 
 63 |     @staticmethod
 64 |     def seach_keyword_chinakaoyan(question_list, question_url):
 65 |         number = 0
 66 |         sum_number = 0
 67 |         for i in question_list:
 68 |             if re.findall(search_profession, i) == [search_profession]:#匹配相同字段，对应链接顺序
 69 |                 #print(i,"---请点击：","http://www.chinakaoyan.com"+question_url[number])
 70 |                 text2.insert('insert',i+"---请去往："+"http://www.chinakaoyan.com"+str(question_url[number]) + "\n"+"\n")
 71 |                 sum_number +=1
 72 |             number = number + 1
 73 |         if sum_number == 0:
 74 |             text2.insert('insert',"目前最新发布中没有搜索到相关内容。"+"\n")
 75 | 
 76 |     @staticmethod
 77 |     def seach_keyword_muchong(question_list, question_url):
 78 |         number = 0
 79 |         sum_number = 0
 80 |         for i in question_list:
 81 |             if re.findall(search_profession, i) == [search_profession]:#匹配相同字段，对应链接顺序
 82 |                 #print(i,"---请点击：",question_url[number])
 83 |                 text2.insert('insert',i+"---请去往："+str(question_url[number])+ "\n"+"\n")
 84 |                 sum_number +=1
 85 |             number = number + 1
 86 |         if sum_number == 0:
 87 |             text2.insert('insert',"目前最新发布中没有搜索到相关内容。"+"\n")
 88 | 
 89 | def run_main():
 90 |     #while 1:#定时60s查询
 91 |         text1.delete(0.0, END)
 92 |         text2.delete(0.0, END)
 93 |         global search_profession
 94 |         search_profession = entry1.get()#获取输入专业
 95 |         muchong_index = 1
 96 |         (title_chinakaoyan,prof_chinakaoyan, url_chinakaoyan) = spider.start_request_chinakaoyan(web_site_chinakaoyan)# 查询 chinakaoyan.com一页
 97 |         #print("\n","小木虫网站信息如下：                      ","\n")
 98 |         while 1: #小木虫三页
 99 |             if muchong_index != 4:
100 |                 web_site_muchong = 'http://muchong.com/bbs/kaoyan.php?action=adjust&type=1&page=' + str(muchong_index)
101 |                 (list_muchong, porf_muchong,url_muchong) = spider.start_request_muchong(web_site_muchong)  # 查询 muchong
102 |                 muchong_index = muchong_index + 1
103 |             else :
104 |                 break
105 |         #print("\n")
106 |         # muchong_index = 1  # 小木虫页面复位
107 |         spider.seach_keyword_chinakaoyan(prof_chinakaoyan, url_chinakaoyan)#对chinakaoyan专业进行关键字查询
108 |         spider.seach_keyword_chinakaoyan(title_chinakaoyan, url_chinakaoyan)#对chinakaoyan学校
109 |         #print("\n")
110 |         spider.seach_keyword_muchong(porf_muchong, url_muchong)#对小木虫学校专业信息进行关键字匹配
111 |         spider.seach_keyword_muchong(list_muchong, url_muchong)#对小木虫学校信息进行关键字匹配
112 |         #print("                                   ","1分钟后将对最新信息进行检索")
113 | 
114 |         #time.sleep(15)
115 | 
116 | spider = Spider()
117 | #GUI
118 | master = Tk()
119 | master.title('考研调剂信息查询1.0   Powered by Dong dong Xu')
120 | master.geometry('1200x650+100+50')#显示框大小与坐标
121 | master.resizable(0, 0)
122 | #标签
123 | label1 = Label(master, text='请输入专业或学校简称：', font=('GB2312', 14))
124 | label1.grid(row=0, column=0, sticky=E)#.grid将内容展示出来
125 | label2 = Label(master, text='Github : https://github.com/Tcloser', font=('GB2312', 14))
126 | label2.grid(row=2, column=1)#.grid将内容展示出来
127 | #输入专业内容框1
128 | entry1 = Entry(master, font=('GB2312', 14), width=30)
129 | entry1.grid(row=0, column=1)
130 | #搜索内容显示框
131 | res = StringVar()
132 | #搜索按钮
133 | button1 = Button(master, text='搜索', font=('GB2312', 14), width=14, command=run_main)#******执行循环
134 | button1.grid(row=0, column=2)
135 | #退出按钮
136 | button2 = Button(master, text='退出', font=('GB2312', 14), width=14, command=master.quit)
137 | button2.grid(row=2, column=2)
138 | #文本显示
139 | text1 = Text(master, font=('GB2312', 12), width=150, height=25)
140 | text1.grid(columnspan=3)
141 | text2 = Text(master, font=('GB2312', 12), width=150, height=10, fg ="red")
142 | text2.grid(columnspan=3)
143 | #显示框
144 | master.mainloop()
145 | 
146 | 
147 | 
148 | 
149 | 
150 | 
151 | 
152 | 
153 | 


--------------------------------------------------------------------------------