广西壮族自治区人民政府

REITs专题数据/policy-guangxi.py

-import json
+import json
@@ -6,10 +6,17 @@ 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 = '广西壮族自治区人民政府'
 headers = {
     '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',
     'Content-Type': 'application/json',
@@ -60,11 +67,9 @@ def getDataJson(page):
 
 
 def getContent(url, publishDate, num):
-    fjhref_list = ''
-    fjtitle_list = ''
-    url_ = url.split('/')[-1]
-    url_ = url.replace(url_, '')
+    id_list = []
     soup = getSoup(url)
+    policy.paserUrl(soup, url)
     contentWithTag = soup.find('div', attrs={'id': 'articleFile'})
     try:
         scripts = contentWithTag.find_all('script')
@@ -79,46 +84,21 @@ def getContent(url, publishDate, num):
     except:
         pass
     content = contentWithTag.text
-    img_list = contentWithTag.find_all('img')
-    num_ = 1
-    for img in img_list:
-        fj_href = img.get('src')
-        fjhref_list += fj_href + '\n'
-        if 'http' not in fj_href:
-            fj_href = url_ + fj_href
-        fj_title = img.get('title')
-        if fj_title == '':
-            fj_title = str(num_)
-        category = os.path.splitext(fj_href)[1]
-        if category not in fj_title:
-            fj_title = fj_title + category
-        fj_title = f'{num}-{publishDate[:10]}-{fj_title}'
-        fjtitle_list += fj_title + '\n'
-        fjcontent = getFjContent(fj_href)
-        file = f'./相关政策/广西壮族自治区人民政府/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')
     a_list = soup.find('div', class_='downloadfile').find_all('a')
     for a in a_list:
         fj_href = a.get('href')
-        if 'http' not in fj_href:
-            fj_href = url_ + 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[:10]}-{fj_title}'
-        fjtitle_list += fj_title + '\n'
-        fjcontent = getFjContent(fj_href)
-        file = f'./相关政策/广西壮族自治区人民政府/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')
-    fjhref_list = fjhref_list.lstrip().strip()
-    fjtitle_list = fjtitle_list.lstrip().strip()
-    return content,fjtitle_list,fjhref_list
+
+        att_id, full_path = policy.attuributefile(fj_title, fj_href, num, publishDate)
+        if att_id:
+            id_list.append(att_id)
+            a['href'] = full_path
+
+    return content, contentWithTag, id_list
 
 
 def getData(data_, num):
@@ -126,20 +106,47 @@ def getData(data_, num):
     publishDate = data_['data']['time']
     origin = '广西壮族自治区人民政府'
     href = data_['data']['url']
+    # 根据链接判重
+    is_member = baseCore.r.sismember('REITs::' + webname, href)
+    if is_member:
+        return
     writtenDate = data_['data']['table-10']
     organ = data_['data']['source']
     pub_hao = data_['data']['table-5']
     summary = data_['data']['table-7']
-    content, fjtitle_list, fjhref_list = getContent(href, publishDate, num)
-    data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
-            fjhref_list]
-    return data
+    content, contentWithTag, id_list = getContent(href, publishDate, num)
+    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': '1729045187128119298',
+    }
+    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/广西壮族自治区人民政府/政策文件'):
-        os.makedirs('./相关政策/广西壮族自治区人民政府/政策文件')
-    data_list = []
     num = 1
     total = getTotal()
     for page in range(1, total + 1):
@@ -149,14 +156,11 @@ def doJob():
             title = data_['data']['title']
             if title not in title_list:
                 title_list.append(title)
-                data = getData(data_, num)
-                data_list.append(data)
-                log.info(f'{title}===采集成功')
+                getData(data_, num)
+
                 num += 1
                 time.sleep(2)
-    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/江西省人民政府/广西壮族自治区人民政府政策文件.xlsx', index=False)
+
 
 
 if __name__ == '__main__':