附件不是文件

REITs专题数据/policy-jilin.py

-import os
+import os
@@ -5,11 +5,17 @@ import numpy as np
 import pandas as pd
 import requests
 from bs4 import BeautifulSoup
-
-from base import BaseCore
+import BaseCore
 
 baseCore = BaseCore.BaseCore()
 log = baseCore.getLogger()
+
+from reits import Policy
+policy = Policy()
+
+
+topic = 'policy'
+webname = '吉林市人民政府'
 headers = {
     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0',
@@ -42,14 +48,14 @@ def getFjContent(url):
     return req.content
 
 
-def getData(num, title, href, origin, publishDate, summary):
-    writtenDate = ''
+def getData(num, title, url, origin, publishDate, summary):
+    id_list = []
+    writtenDate = None
     pub_hao = ''
     organ = ''
-    fjhref_list = ''
-    fjtitle_list = ''
-    ip = baseCore.get_proxy()
-    req = requests.get(href, headers=headers, proxies=ip)
+
+    # ip = baseCore.get_proxy()
+    req = requests.get(url, headers=headers)#, proxies=ip)
     req.encoding = req.apparent_encoding
     soup = BeautifulSoup(req.text, 'html.parser')
     try:
@@ -108,19 +114,17 @@ def getData(num, title, href, origin, publishDate, summary):
             if '.html' in a.get('href') or '.shtml' in a.get('href') or '.htm' in a.get('href'):
                 continue
             href = a.get('href')
-            fjhref_list += href + '\n'
+
             category = os.path.splitext(href)[1]
-            fj_title = f'{num}-{publishDate}-{a.text.lstrip().strip()}'
+            fj_title = a.text.lstrip().strip()
             if '<' in fj_title or '>' in fj_title:
                 fj_title = fj_title.replace('<', '').replace('>', '')
             if category not in fj_title:
                 fj_title = fj_title + category
-            fjtitle_list += fj_title + '\n'
-            fjcontent = getFjContent(href)
-            file = f'./相关政策/内蒙古自治区人民政府/政策文件/{fj_title}'
-            with open(file, 'wb') as f:
-                f.write(fjcontent)
-            log.info(f'{fj_title}===附件下载成功')
+            att_id, full_path = policy.attuributefile(fj_title, href, num, publishDate)
+            if att_id:
+                id_list.append(att_id)
+                a['href'] = full_path
     except:
         pass
     try:
@@ -129,32 +133,59 @@ def getData(num, title, href, origin, publishDate, summary):
             if '.html' in a.get('href') or '.shtml' in a.get('href') or '.htm' in a.get('href'):
                 continue
             href = a.get('href')
-            fjhref_list += href + '\n'
+
             category = os.path.splitext(href)[1]
-            fj_title = f'{num}-{publishDate}-{a.text.lstrip().strip()}'
+            fj_title = a.text.lstrip().strip()
             if '<' in fj_title or '>' in fj_title:
                 fj_title = fj_title.replace('<', '').replace('>', '')
             if category not in fj_title:
                 fj_title = fj_title + category
-            fjtitle_list += fj_title + '\n'
-            fjcontent = getFjContent(href)
-            file = f'./相关政策/内蒙古自治区人民政府/政策文件/{fj_title}'
-            with open(file, 'wb') as f:
-                f.write(fjcontent)
-            log.info(f'{fj_title}===附件下载成功')
+            att_id, full_path = policy.attuributefile(fj_title, href, num, publishDate)
+            if att_id:
+                id_list.append(att_id)
+                a['href'] = full_path
+            else:
+                return
     except:
         pass
-
-    content = contentWithTag.text.lstrip().strip()
-    data_ = [num, title, writtenDate, origin, href, publishDate, organ, pub_hao, summary, content, fjtitle_list,
-             fjhref_list]
-    return data_
+    try:
+        content = contentWithTag.text.lstrip().strip()
+    except:
+        log.info(url)
+        return
+    contentWithTag_str = str(contentWithTag)
+    time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+    dic_info = {
+        'attachmentIds': id_list,
+        'author': '',
+        'content': content,
+        'contentWithTag': contentWithTag_str,
+        'deleteFlag': 0,
+        'id': '',
+        'title': title,
+        'publishDate': publishDate,
+        'origin': origin,
+        'sourceAddress': url,
+        'writtenDate': writtenDate,
+        'organ': organ,
+        'topicClassification': '',
+        'issuedNumber': pub_hao,
+        'summary': summary,
+        'createDate': time_now,
+        'sid': '1729042375596158978',
+    }
+    try:
+        baseCore.sendkafka(dic_info, topic)
+        baseCore.r.sadd('REITs::' + webname, url)
+        log.info(f'采集成功--{title}--{url}')
+    except Exception as e:
+        for att_id in id_list:
+            baseCore.deliteATT(att_id)
+    return
 
 
 def doJob():
-    if not os.path.exists('./相关政策/吉林省人民政府/政策文件'):
-        os.makedirs('./相关政策/吉林省人民政府/政策文件')
-    data_list = []
+
     num = 1
     url = 'https://intellsearch.jl.gov.cn/api/data/list'
     total = getTotal(url)
@@ -164,17 +195,17 @@ def doJob():
             title = data_['title']
             title = BeautifulSoup(title, 'lxml').find('p').text.lstrip().strip()
             href = data_['url']
+            # 根据链接判重
+            is_member = baseCore.r.sismember('REITs::' + webname, href)
+            if is_member:
+                continue
             origin = data_['websiteName']
             publishDate = data_['pubtime'].replace('/', '-')
             summary = data_['content']
             summary = BeautifulSoup(summary, 'lxml').find('p').text.lstrip().strip()
             data = getData(num, title, href, origin, publishDate, summary)
-            data_list.append(data)
+            # data_list.append(data)
             num += 1
-    df = pd.DataFrame(np.array(data_list))
-    df.columns = ['序号', '标题', '发布时间', '来源', '原文链接', '发文时间', '发文机构', '发文字号', '摘要', '正文', '附件名称', '附件连接']
-    df.to_excel('./吉林省人民政府政策文件.xlsx', index=False)
-
 
 if __name__ == '__main__':
     doJob()

REITs专题数据/policy-tianjin.py

-import os
+import os
@@ -125,6 +125,9 @@ def getContent(num, title, pub_time, origin, organ, url, pub_hao, summary):
             if att_id:
                 id_list.append(att_id)
                 a['href'] = full_path
+            else:
+                log.info(f'附件解析失败==={url}')
+                return
     except:
         pass
     # try:

REITs专题数据/reits.py

-import os
+import os
@@ -113,7 +113,11 @@ class Policy():
             else:
                 return '', ''
             att_id, full_path = baseCore.tableUpdate(retData, 'RETIs文件', file_name, num, publishDate)
-            return att_id,full_path
+            return att_id, full_path
+        else:
+            log.info('不是文件格式')
+            return '', ''
+
 
 
     def downloadfile(self,file_href,path):