11.29

REITs专题数据/policy-gwy.py

-import os
+import os
 import os
 import time
 
-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 = '中华人民共和国中央人民政府'
 headers = {
     'Accept': 'application/json, text/plain, */*',
     'Accept-Encoding': 'gzip, deflate, br',
@@ -84,9 +89,8 @@ def getDataJson(page, types):
     return data_list
 
 
-def getContent(url, publishDate, num, organ):
-    fjhref_list = ''
-    fjtitle_list = ''
+def getContent(url, publishDate, num, organ, id_list):
+
     soup = getSoup(url)
     if organ == '':
         try:
@@ -100,18 +104,18 @@ def getContent(url, publishDate, num, organ):
     for a in a_list:
         fj_href = a.get('href')
         if '.htm' not in fj_href and '.html' not in fj_href and '.shtml' not in fj_href and '.shtm' not in fj_href:
-            fjhref_list += fj_href + '\n'
+
             fj_title = a.text.lstrip().strip()
             category = os.path.splitext(fj_href)[1]
             if category not in fj_title:
                 fj_title = fj_title + category
-            fj_title = f'{num}-{publishDate}-{fj_title}'
-            fjtitle_list += fj_title + '\n'
-            fjcontent = getFjContent(fj_href)
-            file = f'./相关政策/国务院/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')
+
+            # 上传附件至obs
+            att_id, full_path = policy.attuributefile(fj_title, fj_href, num, publishDate)
+            if att_id:
+                id_list.append(att_id)
+                a['href'] = full_path
+
     try:
         scripts = contentWithTag.find_all('script')
         for script in scripts:
@@ -125,15 +129,17 @@ def getContent(url, publishDate, num, organ):
     except:
         pass
     content = contentWithTag.text.lstrip().strip()
-    return content, fjtitle_list, fjhref_list, organ
+    return content, id_list, contentWithTag, organ
 
 
 def getData(data_, num):
+    id_list = []
     title = data_['title'].replace('\n', '').replace('\r', '')
     title = BeautifulSoup(title,'lxml').text
     publishDate = data_['pubtimeStr'].replace('.', '-')
     origin = '国务院'
     href = data_['url']
+
     writtenDate = data_['ptime']
     try:
         organ = data_['puborg']
@@ -142,16 +148,43 @@ def getData(data_, num):
     pub_hao = data_['pcode']
     summary = data_['summary']
     summary = BeautifulSoup(summary, 'lxml').text.lstrip().strip()
-    content, fjtitle_list, fjhref_list, organ = getContent(href, publishDate, num, organ)
-    data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
-            fjhref_list]
-    return data
+    content, id_list, contentWithTag, organ = getContent(href, publishDate, num, organ, id_list)
+    time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+    dic_info = {
+        'attachmentIds': id_list,
+        'author': '',
+        'content': content,
+        'contentWithTag': str(contentWithTag),
+        'deleteFlag': 0,
+        'id': '',
+        'title': title,
+        'publishDate': publishDate,
+        'origin': origin,
+        'sourceAddress': href,
+        'writtenDate': writtenDate,
+        'organ': organ,
+        'topicClassification': '',
+        'issuedNumber': pub_hao,
+        'summary': summary,
+        'createDate': time_now,
+        'sid': '1729028548502597633',
+    }
+    try:
+        baseCore.sendkafka(dic_info, topic)
+        baseCore.r.sadd('REITs::' + webname, href)
+        log.info(f'采集成功--{title}--{href}')
+    except:
+        for att_id in id_list:
+            baseCore.deliteATT(att_id)
+
+    # data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
+    #         fjhref_list]
 
 
 def doJob():
-    if not os.path.exists('./相关政策/国务院/政策文件'):
-        os.makedirs('./相关政策/国务院/政策文件')
-    data_list = []
+    # if not os.path.exists('./相关政策/国务院/政策文件'):
+    #     os.makedirs('./相关政策/国务院/政策文件')
+    # data_list = []
     href_list = []
     num = 1
     types = ['bumenfile', 'gongwen', 'otherfile', 'gongbao']
@@ -160,16 +193,19 @@ def doJob():
         data_json = getDataJson(page, types)
         for data_ in data_json:
             href = data_['url']
+            # 根据链接判重
+            is_member = baseCore.r.sismember('REITs::' + webname, href)
+            if is_member:
+                continue
             if href not in href_list:
-                data = getData(data_, num)
+                getData(data_, num)
                 num += 1
-                data_list.append(data)
+                # data_list.append(data)
                 href_list.append(href)
-                log.info(f'{data[1]}===采集成功')
             time.sleep(3)
-    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('./相关政策/国务院/国务院政策文件.xlsx', index=False)
+    # 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('./相关政策/国务院/国务院政策文件.xlsx', index=False)
 
 
 if __name__ == '__main__':