python3 爬取百合网的女人们和男人们

  1 #__author: "YuWei"
  2 #__date: 2018/2/4
  3 import requests
  4 import time
  5 import pymssql
  6 import os
  7 
  8 # 8个人为一组，该常量用于判断列表的长度是否与网站一致
  9 FING_INDEX = 8
 10 # 请求头，伪装成浏览器
 11 HEADERS = {‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0‘}
 12 # 代理ip，防止被百合网封ip
 13 HTTP_IP_PROXIES_1 = ‘http://211.151.58.5:80‘
 14 HTTP_IP_PROXIES_2 = ‘http://192.168.200.1:8081‘
 15 
 16 def baihe_db(personal):
 17     """
 18     数据库相关的操作
 19 
 20     :param personal: 为字典类型，封装着个人具体信息
 21     :return: 无
 22     """
 23     # 数据连接
 24     conn = pymssql.connect(host=‘localhost‘, user=‘YUANWEI‘, password=‘13974162858x‘, database=‘Baihe‘,charset=‘utf8‘)
 25     cur = conn.cursor() # 游标
 26     sql = """insert into users values({},‘{}‘,{},‘{}‘,‘{}‘,‘{}‘,{},‘{}‘,‘{}‘,‘{}‘,‘{}‘);"""  27         .format(personal[‘userID‘], personal[‘nickname‘], personal[‘age‘], ‘男‘ if personal[‘gender‘] == "1" else ‘女‘,
 28                 personal[‘cityChn‘], personal[‘educationChn‘], personal[‘height‘],
 29                 ‘没房‘ if personal[‘housing‘] == 0 else ‘有房‘, ‘没车‘ if personal[‘car‘] == 0 else ‘有车‘,
 30                 personal[‘incomeChn‘],personal[‘marriageChn‘])
 31     print(‘sql: ‘, sql)
 32     try:
 33         cur.execute(sql) # 执行sql语句
 34         save_photo(personal, get_miss_photo_binary(personal[‘headPhotoUrl‘])) # 保存头像
 35         print(‘成功获取该用户‘,personal[‘userID‘])
 36     except pymssql.IntegrityError:
 37         print(‘该用户已存在 ‘,personal[‘userID‘])
 38     except SystemError as sy: # 向err.txt导入错误日志
 39         with open(‘err.txt‘,‘a‘,encoding=‘utf8‘) as file:
 40             file.write(personal[‘nickname‘] + ‘ ‘ + str(personal[‘userID‘]) + ‘ 错误信息：‘ + str(sy) + ‘\n‘) # 写
 41     conn.commit() # 提交
 42     time.sleep(1)
 43     cur.close()
 44     conn.close()
 45 
 46 def personal_data(lists):
 47     """
 48     获取一组的详细信息，最多为8个
 49 
 50     :param lists: 列表类型，封装着一组信息
 51     :return: 无
 52     """
 53     for personal_data_dict in lists: # 遍历一组信息
 54         baihe_db(personal_data_dict)
 55 
 56 def get_miss_photo_binary(photo_url):
 57     """
 58     获取照片的二进制数据
 59 
 60     :param photo_url: 个人头像的url
 61     :return: 二进制数据
 62     """
 63     binary = ‘‘
 64     try:
 65         # 向服务器发送get请求,下载图片的二进制数据
 66         binary = requests.get(photo_url, headers=HEADERS,proxies={"http": HTTP_IP_PROXIES_2}).content
 67     except requests.exceptions.MissingSchema as rem:
 68         print(rem)
 69     except requests.exceptions.ProxyError: # 代理网络连接慢或无网络
 70         time.sleep(5)
 71         # 递归调用get_miss_photo_binary()
 72         get_miss_photo_binary(photo_url)
 73     return binary
 74 
 75 def save_photo(personal,binary):
 76     """
 77     以‘E:/Baihe/1/‘为文件目录路径 或 以‘E:/Baihe/0/‘为文件目录路径
 78     以 name + id + .jpg 或 以 id + .jpg 为文件名
 79     有可能无相片
 80 
 81     :param personal: 字典类型，封装着个人具体信息
 82     :param binary: 二进制数据
 83     :return: 无
 84     """
 85     if binary != ‘‘:
 86         file_path = ‘E:/Baihe/1/‘ if personal[‘gender‘] == "1" else ‘E:/Baihe/0/‘ #
 87         if not os.path.exists(file_path): # 如果该路径不存在
 88             os.makedirs(file_path) # 创建该路径
 89         try:
 90             # 向file_path路径保存图片
 91             with open(file_path + personal[‘nickname‘] + str(personal[‘userID‘]) + ‘.jpg‘,‘wb‘) as file:
 92                 file.write(binary)
 93         except OSError:
 94             with open(file_path + str(personal[‘userID‘]) + ‘.jpg‘,‘wb‘) as file:
 95                 file.write(binary)
 96 
 97 
 98 def no_exact_division(miss_id_list):
 99     """
100    当包含用户id的列表长度不能被8整除且列表长度小于8时调用该方法
101 
102     :param miss_id_list: 为列表类型，封装着用户id
103     :return: 无
104     """
105     miss_info_lists = ba.get_miss_info(miss_id_list)  # 获取列表的个人信息
106     personal_data(miss_info_lists) # 遍历一组的信息
107 
108 
109 class Baihe(object):
110 
111     def __init__(self,account,password):
112         """
113         初始化
114         :param account: 账号
115         :param password: 密码
116         """
117         self.is_begin = True # 开始爬取数据
118         self.index = 0 # 控制self.info长度为8个
119         self.info = [] # 临时保存用户id
120         self.page = 29 # 页码
121         self.account = account # 账号
122         self.password = password # 密码
123         self.req = requests.session() # 会话，保证Cookie一致
124 
125     def login(self):
126        """
127        登录
128 
129        :return: 无
130        """
131        # 登录的url
132        url_login = ‘http://my.baihe.com/Getinterlogin/gotoLogin?event=3&spmp=4.20.87.225.1049&‘ 133                    ‘txtLoginEMail={}&txtLoginPwd={}‘.format(self.account,self.password)
134        login_dict = {}
135        try:
136            # 向服务器发送get请求
137            login_dict = self.req.get(url_login,headers=HEADERS,proxies={"http": HTTP_IP_PROXIES_1},timeout=500).json()
138        except requests.exceptions.ProxyError:  # 代理网络连接慢或无网络
139             time.sleep(5)
140             # 递归调用self.login()
141             self.login()
142        time.sleep(3)
143        print(‘login: ‘,login_dict)
144        self.req.keep_alive = False # 关闭会话多余的连接
145        if login_dict[‘data‘] == 1:
146            print(‘登录成功‘)
147        else:
148            print(‘登录失败, 30分钟以后自动登录。。。。。。。。‘)
149            time.sleep(1800)
150            # 递归调用self.login()
151            self.login()
152        print(‘login is cookie ‘, requests.utils.dict_from_cookiejar(self.req.cookies)) # 查看登录后的会话cookie
153 
154     def filtrate_miss(self,pages):
155         """
156         根据条件筛选数据，不提供条件参数
157 
158         :param pages: 页码。该网站只提供62页的数据
159         :return: 包含160个用户的id的列表
160         """
161         time.sleep(2)
162         # 获取用户id的url
163         url_miss = ‘http://search.baihe.com/Search/getUserID‘
164         # from表单数据
165         params_miss = {"minAge": 18, "maxAge": 85, "minHeight": 144, "maxHeight": 210, "education": ‘1-8‘,
166                        "income": ‘1-12‘, "city": -1, "hasPhoto": 1, "page": pages, "sorterField": 1}
167         miss_dict = {}
168         try:
169             # 发送post请求
170             miss_dict = self.req.post(url_miss,data=params_miss,headers=HEADERS,proxies={‘http‘:HTTP_IP_PROXIES_2}).json()
171         except requests.exceptions.ProxyError:  # 代理网络连接慢或无网络
172             time.sleep(5)
173             # 递归调用self.filtrate_miss()
174             self.filtrate_miss(pages)
175         time.sleep(2)
176         print(‘miss is cookies ‘, requests.utils.dict_from_cookiejar(self.req.cookies)) # 查看筛选后的会话cookie
177         print(‘miss dict: ‘,miss_dict)
178         print(len(miss_dict[‘data‘]),‘个‘)
179         return miss_dict[‘data‘]
180 
181     def get_miss_info(self,infos):
182         """
183         获取用户详细信息
184 
185         :param infos: 列表类型，封装着个人id，可能为一组（8），或小于8个
186         :return: 包含一组的详细信息
187         """
188         if len(infos) == FING_INDEX: # infos列表长度等于8时
189             url_info = ‘http://search.baihe.com/search/getUserList?userIDs={},{},{},{},{},{},{},{}‘190                 .format(infos[0],infos[1],infos[2],infos[3],infos[4],infos[5],infos[6],infos[7])
191         else: # infos列表长度小于8时
192             bracket = ‘‘ # 参数userIDs的值
193             for lens in range(len(infos)):
194                 bracket += (str(infos[lens]) + ‘,‘) # 构造该表示："{},{},{},{},{},{},{},{},"
195             # 获取用户详细信息的url      bracket[:len(bracket)-1]： 分片，干掉最后一个“,”
196             url_info = ‘http://search.baihe.com/search/getUserList?userIDs=‘ + bracket[:len(bracket)-1]
197         miss_info = {}
198         try:
199             # 发送post请求
200             miss_info = self.req.post(url_info,headers=HEADERS,proxies={‘http‘:HTTP_IP_PROXIES_2}).json()
201         except requests.exceptions.ProxyError:  # 代理网络连接慢或无网络
202             time.sleep(5)
203             # 递归调用self.get_miss_info()
204             self.get_miss_info(infos)
205         time.sleep(2)
206         return miss_info[‘data‘]
207 
208     def exact_division(self,miss_id_list):
209         """
210         当包含用户id的列表长度能被8整除或包含用户id的列表长度不能被8整除且包含用户id的列表长度大于8
211 
212         :param miss_id_list: id信息列表（160）
213         :return: 无
214         """
215         for user_id in miss_id_list:
216             self.index += 1
217             self.info.append(user_id)
218             if ba.index == FING_INDEX:
219                 print(‘user id: ‘, self.info)
220                 miss_info_list = ba.get_miss_info(self.info) # 8
221                 if None != miss_info_list:
222                     # 使self.index，self.info为初值，以便8人一组
223                     self.index = 0
224                     self.info = []
225                     print(‘miss info list: ‘, miss_info_list)
226                     personal_data(miss_info_list) # 遍历一组（8）的信息
227                 else:
228                     print(‘miss info list is null‘)
229                     continue
230 
231     def main(self):
232         """
233         具体实施
234 
235         :return: 无
236         """
237         self.login() # 登录
238         while self.is_begin: # 开始
239             print(‘正在获取‘,self.page,‘页.......‘)
240             miss_id_list = self.filtrate_miss(self.page) # 获取用户id列表
241             if len(miss_id_list) != 0: # 列表有id
242                 num = len(miss_id_list) % FING_INDEX # 模运算
243                 if num == 0: # 被8整除
244                     self.exact_division(miss_id_list)
245                 else: # 没有被8整除 , 虽然该分支没有执行，但还是要加上。因为该网站总是提供160个id
246                     print(‘余数: ‘,num)
247                     if len(miss_id_list) > FING_INDEX: # id列表的长度大于8
248                         copy_miss_id_list = miss_id_list[:len(miss_id_list) - num] # 分片 取8个一组
249                         self.exact_division(copy_miss_id_list)
250                         no_exact_division(miss_id_list[len(miss_id_list) - num:]) # 余下的个人信息
251                     else:
252                         no_exact_division(miss_id_list) # 小于8个人的个人的信息
253             else:
254                 print(‘数据已爬完。。。。。‘)
255                 self.is_begin = False
256             self.page += 1
257             time.sleep(10)
258 # 运行
259 if __name__ == ‘__main__‘:
260     ba = Baihe(‘xxxxxxxxx‘, ‘xxxxxxxxx‘) # 账号 密码
261     ba.main()