云南省人民政府

REITs专题数据/policy-yunnan.py

-import os
+import os
@@ -10,10 +10,17 @@ from bs4 import BeautifulSoup
 from retry import retry
 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 = '云南省人民政府'
 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',
 }
@@ -36,9 +43,9 @@ def getFjContent(url):
 
 
 def getContent(url, publishDate, num):
-    fjhref_list = ''
-    fjtitle_list = ''
+    id_list = []
     soup = getSoup(url)
+    policy.paserUrl(soup, url)
     contentWithTag = soup.find('div', class_='content')
     if not contentWithTag:
         contentWithTag = soup.find('div', class_='TRS_UEDITOR')
@@ -62,24 +69,18 @@ def getContent(url, publishDate, num):
         fj_href = a.get('href')
         if 'http' not in fj_href:
             fj_href = 'https://www.yn.gov.cn' + fj_href
-        fjhref_list += fj_href + '\n'
+
         if fj_title == '':
             fj_title = str(num_)
             num_ += 1
         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/云南省人民政府/政策文件/{fj_title}'
-        if os.path.exists(file):
-            fj_title = fj_title.replace(category, f'-{num_}{category}')
-            num_ += 1
-        file = f'./相关政策/云南省人民政府/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
+
     try:
         a_list = soup.find('ul', class_='apfile').find_all('a')
         for a in a_list:
@@ -87,39 +88,38 @@ def getContent(url, publishDate, num):
             fj_href = a.get('href')
             if 'http' not in fj_href:
                 fj_href = 'https://www.yn.gov.cn' + fj_href
-            fjhref_list += fj_href + '\n'
+
             if fj_title == '':
                 fj_title = str(num_)
                 num_ += 1
             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/云南省人民政府/政策文件/{fj_title}'
-            if os.path.exists(file):
-                fj_title = fj_title.replace(category, f'-{num_}{category}')
-                num_ += 1
-            file = f'./相关政策/云南省人民政府/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
     except:
         pass
-    return content, fjtitle_list, fjhref_list
+    return content, contentWithTag, id_list
 
 
 def getData(div, num):
+
     pattern = r"\d{4}-\d{2}-\d{2}"
     title = div.find_element(By.CLASS_NAME, 'title').find_element(By.CLASS_NAME, 'fontlan').get_attribute(
         'title').lstrip().strip()
     href = div.find_element(By.CLASS_NAME, 'fontlan').get_attribute('href')
+
+    # 根据链接判重
+    is_member = baseCore.r.sismember('REITs::' + webname, href)
+    if is_member:
+        return
     origin = '云南省人民政府'
     try:
         publishDate = re.findall(pattern, div.find_element(By.CLASS_NAME, 'content').text)[0]
     except:
-        publishDate = ''
+        publishDate = None
     try:
         organ = \
             div.find_element(By.CLASS_NAME, 'rowtab').find_elements(By.TAG_NAME, 'div')[0].find_elements(By.TAG_NAME,
@@ -135,30 +135,52 @@ def getData(div, num):
         organ = ''
         pub_hao = ''
     summary = ''
-    writtenDate = ''
+    writtenDate = None
     if '.pdf' in href or '.PDF' in href:
+        id_list = []
         content = ''
-        fjhref_list = href
+        contentWithTag_str = ''
+        fj_href = href
         fj_title = title + '.pdf'
-        fjcontent = getFjContent(fjhref_list)
-        file = f'./相关政策/云南省人民政府/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')
-        fjtitle_list = fj_title
+        att_id, full_path = policy.attuributefile(fj_title, fj_href, num, publishDate)
+        if att_id:
+            id_list.append(att_id)
     else:
-        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': '1729046848292892673',
+    }
+    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/云南省人民政府/政策文件'):
-        os.makedirs('./相关政策/云南省人民政府/政策文件')
-    data_list = []
+
     url = 'https://sheng.so-gov.cn/s?siteCode=5300000033&qt=REITs'
-    driver = baseCore.buildDriver()
+    driver = policy.createDriver()
     driver.get(url)
     time.sleep(2)
     num = 1
@@ -176,17 +198,13 @@ def doJob():
             time.sleep(2)
             div_list = driver.find_elements(By.XPATH, '//*[@id="results"]/div')
             for div in div_list:
-                data = getData(div, num)
-                data_list.append(data)
-                log.info(f'{data[1]}===采集成功')
+                getData(div, num)
                 num += 1
             try:
                 driver.find_element(By.CLASS_NAME, 'pagination').find_element(By.CLASS_NAME, 'next').click()
             except:
                 pass
-    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/云南省人民政府/云南省人民政府政策文件.xlsx', index=False)
+
 
 
 if __name__ == '__main__':