11/15

REITs专题数据/reits.py

-import os
+import os
@@ -388,7 +388,7 @@ def zhengquanqihuo(wb,file_path):
 
 
 #上海交易所 http://www.sse.com.cn/home/search/index.shtml?webswd=REITs
-def sse():
+def sse(wb,file_path):
     url = 'http://query.sse.com.cn/search/getESSearchDoc.do?page=0&limit=10&publishTimeEnd=&publishTimeStart=&orderByDirection=DESC&orderByKey=score&searchMode=fuzzy&spaceId=3&keyword=REITs&siteName=sse&keywordPosition=title%2Cpaper_content&channelId=10001&channelCode=8640%2C8641%2C8642%2C8643%2C8644%2C8645%2C8646%2C8647%2C8648%2C8649%2C8650%2C8651%2C8652%2C8653%2C8654%2C8655%2C8656%2C8657%2C8658%2C8659%2C8660%2C8661%2C8685%2C9348%2C12632%2C12768%2C12769%2C12770%2C12771%2C12772%2C12773%2C12774%2C12775%2C12776%2C12777%2C12778%2C12779%2C12780%2C12781%2C12782%2C12783%2C12784%2C12785%2C12786%2C12787%2C12788%2C12789%2C12790%2C12791%2C12792%2C12793%2C12794%2C12795%2C12796%2C12797%2C12798%2C12799%2C12800%2C12801%2C12802%2C12803%2C12804%2C12805%2C12806%2C12807%2C12808%2C12809%2C12810%2C12811%2C12812%2C13061%2C13282%2C13283%2C13284%2C13285%2C13286%2C13287%2C13288%2C13289%2C13294%2C13364%2C13365%2C13366%2C13367%2C14595%2C14596%2C14597%2C14598%2C14599%2C14600%2C14601%2C14602%2C14603%2C14604%2C14605%2C14606&trackId=50619067167713018335655119683810&_=1699508921761'
     headers = {
         'Accept': '*/*',
@@ -454,7 +454,7 @@ def sse():
                     '原文链接': newsUrl,
                     '发文时间': '',
                     '发文机构': '',
-                    '发文字号': pubHao,
+                    '发文字号': '',
                     '摘要': summary,
                     '正文': content,
                     '附件名称': fu_jian_name,
@@ -468,10 +468,13 @@ def sse():
                 # print(content_)
                 # #  将链接替换为绝对路径
                 contentWithTag = policy.paserUrl(content_, newsUrl)
-                pubHao = contentWithTag.find('p',style='text-align: center;').text.strip(' ')
-                if '〔' in pubHao:
-                    pass
-                else:
+                try:
+                    pubHao = contentWithTag.find('p',style='text-align: center;').text.strip(' ')
+                    if '〔' in pubHao:
+                        pass
+                    else:
+                        pubHao = ''
+                except:
                     pubHao = ''
                 # print(contentWithTag)
                 content = contentWithTag.text
@@ -482,11 +485,18 @@ def sse():
                 for fujian in fujian_list:
                     file_href = fujian['href']
                     file_name = fujian.text.strip(' ')
-                    rename_file = f'{str(num)}_{publishDate}_{file_name}'
+                    category = os.path.splitext(file_href)[1]
+                    if category in file_name:
+                        pass
+                    else:
+                        file_name = file_name + category
+                    rename_file = f'{str(num)}_{publishDate}_{file_name}'.replace('\\','').replace('/','').replace('|','').replace('>','').replace('<','').replace('*','').replace('：','').replace('？','').replace('—','')
                     fu_jian_name += rename_file + '\n'
                     fu_jian_href += file_href + '\n'
-                    policy.downloadfile(file_href, f'{path}/{rename_file}')
-
+                    try:
+                        policy.downloadfile(file_href, f'{path}/{rename_file}')
+                    except:
+                        log.info(f'--{page}-{num}======{newsUrl}')
                 dic_info = {
                     '序号': num,
                     '标题': title,
@@ -615,8 +625,9 @@ def beijing():
 
 
 if __name__=="__main__":
-    file_path = f'data/REITs专题数据.xlsx'
+    file_path = f'data/REITs国家改革发展委员会.xlsx'
     wb = policy.createfile(file_path)
     # reform(wb,file_path)
-    zhengquanqihuo(wb,file_path)
+    # zhengquanqihuo(wb,file_path)
+    sse(wb,file_path)
 # zhengquanqihuo()
\ No newline at end of file

base/BaseCore.py

 # 核心工具包
 import os
 import random
+import smtplib
 import socket
 import sys
 import time
+from email.header import Header
+from email.mime.application import MIMEApplication
+from email.mime.multipart import MIMEMultipart
+from email.mime.text import MIMEText
 
 import MySQLdb
 import logbook
@@ -852,3 +857,34 @@ class BaseCore:
         result = obsClient.putContent('zzsn', pathType + name, content=response.content)
         # resp = obsClient.putFile('zzsn', pathType + name, file_path='要上传的那个文件的本地路径')
         return result
+
+    def sendEmail(self, file_name):
+
+        file = open(file_name, 'rb').read()
+        # 发送邮箱地址
+        sender = '1195236739@qq.com'
+        # 接收邮箱地址
+        receiver = '1074481431@qq.com'
+        smtpserver = 'smtp.qq.com'
+        # 发送邮箱登录 账户 密码
+        username = '1195236739@qq.com'
+        password = 'gatvszshadvpgjci'
+
+        maile_title = '企业基本信息采集情况'
+
+        message = MIMEMultipart()
+        message['From'] = sender
+        message['To'] = receiver
+        message['Subject'] = Header(maile_title, 'utf-8')
+
+        message.attach(MIMEText('企业基本信息采集情况', 'plain', 'utf-8'))
+
+        xlsxApart = MIMEApplication(file)
+        xlsxApart.add_header('Content-Disposition', 'attachment', filename='企业基本信息采集情况.xlsx')
+        message.attach(xlsxApart)
+        smtpObj = smtplib.SMTP_SSL(smtpserver)  # 注意：如果遇到发送失败的情况（提示远程主机拒接连接），这里要使用SMTP_SSL方法
+        smtpObj.connect(smtpserver, port=465)
+        smtpObj.login(username, password)
+        smtpObj.sendmail(sender, receiver, message.as_string())
+        print("邮件发送成功！！！")
+        smtpObj.quit()