上海市人民政府

REITs专题数据/policy-shanghai.py

-import json
+import json
@@ -8,10 +8,17 @@ import requests
 from bs4 import BeautifulSoup
 from selenium.webdriver.common.by import By
 
-from base import BaseCore
+import BaseCore
 
 baseCore = BaseCore.BaseCore()
 log = baseCore.getLogger()
+
+from reits import Policy
+policy = Policy()
+
+
+topic = 'policy'
+webname = '上海市人民政府'
 headers = {
     'Accept': '*/*',
     'Accept-Encoding': 'gzip, deflate, br',
@@ -54,17 +61,21 @@ def getFjContent(url):
 
 
 def getData(data_, driver, num):
-    fjhref_list = ''
-    fjtitle_list = ''
+    id_list = []
     title = data_['title']['raw']
     publishDate = data_['date']['raw']
     origin = '上海市人民政府'
     href = data_['url']['raw']
+    # 根据链接判重
+    is_member = baseCore.r.sismember('REITs::' + webname, href)
+    if is_member:
+        return
     organ = data_['fwjg']['raw']
     pub_hao = data_['wh']['raw']
     summary = data_['content']['snippet']
     driver.get(href)
     time.sleep(1)
+    contentWithTag = driver.find_element(By.CLASS_NAME, 'Article_content')
     content = driver.find_element(By.CLASS_NAME, 'Article_content').text.lstrip().strip()
     timeTag = driver.find_element(By.CLASS_NAME, 'PBtime').text
     try:
@@ -76,47 +87,71 @@ def getData(data_, driver, num):
         except:
             writtenDate = timeTag.split('印发日期：')[1].lstrip().strip()
     except:
-        writtenDate = ''
+        writtenDate = None
     try:
         a_list = driver.find_element(By.CLASS_NAME, 'gaoj-list').find_elements(By.TAG_NAME, 'a')
         for a in a_list:
             fj_href = a.get_attribute('href')
-            fjhref_list += fj_href + '\n'
-            category = os.path.splitext(href)[1]
-            fj_title = f'{num}-{publishDate}-{a.text.lstrip().strip()}'
+
+            category = os.path.splitext(fj_href)[1]
+            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, fj_href, num, publishDate)
+            if att_id:
+                id_list.append(att_id)
+                a['href'] = full_path
+            else:
+                pass
     except:
         pass
-    data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
-            fjhref_list]
-    return data
+    # data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
+    #         fjhref_list]
+    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': href,
+        'writtenDate': writtenDate,
+        'organ': organ,
+        'topicClassification': '',
+        'issuedNumber': pub_hao,
+        'summary': summary,
+        'createDate': time_now,
+        'sid': '1729042751554506754',
+    }
+    try:
+        baseCore.sendkafka(dic_info, topic)
+        baseCore.r.sadd('REITs::' + webname, href)
+        log.info(f'采集成功--{title}--{href}')
+    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/上海市人民政府/政策文件'):
-        os.makedirs('./相关政策/上海市人民政府/政策文件')
-    driver = baseCore.buildDriver()
-    data_list = []
+
+    # driver = baseCore.buildDriver()
+    driver = policy.createDriver()
+
     num = 1
     data_json = getDataJson()
     for data_ in data_json:
         data = getData(data_, driver, num)
-        log.info(f'{data[1]}===采集成功')
-        data_list.append(data)
+        # log.info(f'{data[1]}===采集成功')
+        # 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('./相关政策/上海市人民政府/上海市人民政府政策文件.xlsx', index=False)
-
 
 if __name__ == '__main__':
     doJob()