1/24

base/BaseCore.py

@@ -932,7 +932,7 @@ class BaseCore:
         # 发送邮箱地址
         sender = '1195236739@qq.com'
         # 接收邮箱地址
-        receiver = '1007765445@qq.com'
+        receiver = 'fujunxue@ciglobal.cn'
         smtpserver = 'smtp.qq.com'
         # 发送邮箱登录 账户 密码
         username = '1195236739@qq.com'

comData/YanBao/resentYanbao.py

@@ -902,7 +902,7 @@ def qianyanzhishiku():
 def shijiejingjiluntan():
     allnum = {'一': '01', '二': '02', '三': '03', '四': '04', '五': '05', '六': '06', '七': '07', '八': '08', '九': '09', '十': '10', '十一': '11', '十二': '12'}
 
-    for i in range(2, 3):
+    for i in range(1, 3):
 
         # res = requests.get(url)
         # soup = BeautifulSoup(res.content,'html.parser')

comData/policylaw/gwyfile.py

@@ -169,7 +169,7 @@ def get_content1():
                         'id': '',  #
                         'labels': [{'relationId': "1766", 'relationName': "国务院文件", 'labelMark': "policy"}],
                         # 关联标签id  关联标签名称  关联标签标识
-                        'origin': '',  # 政策发布机关
+                        'origin': '中华人民共和国中央人民政府',  # 政策发布机关
                         'organ': pub_org,  # 政策发文机关
                         'topicClassification': child_type,  # 政策文件分类
                         'issuedNumber': pub_code,  # 发文字号

comData/policylaw/gwyparts.py

@@ -151,7 +151,7 @@ def get_content2():
                     'id': '',  #
                     'labels': [{'relationId': "1699", 'relationName': "国务院各部委文件", 'labelMark': "policy"}],
                     # 关联标签id  关联标签名称  关联标签标识
-                    'origin': '',  # 政策发布机关
+                    'origin': '中华人民共和国中央人民政府',  # 政策发布机关
                     'organ': pub_org,  # 政策发文机关
                     'topicClassification': child_type,  # 政策文件分类
                     'issuedNumber': pub_code,  # 发文字号

qiushi_leaderspeech.py

@@ -119,15 +119,15 @@ if __name__=='__main__':
                     #     or '中共' in author or '记者' in author or '新闻社' in author\
                     #     or '党委' in author or '调研组' in author or '研究中心' in author\
                     #     or '委员会' in author or '博物' in author or '大学' in author or '联合会' in author :
-                    if '（' in author or '本刊' in author  \
-                            or '记者' in author or '新闻社' in author \
-                            or '”' in author\
-                            or '大学' in author or '洛桑江村' in author:
-                        continue
-                    # if '国资委党委' in author:
-                    #     pass
-                    # else:
+                    # if '（' in author or '本刊' in author  \
+                    #         or '记者' in author or '新闻社' in author \
+                    #         or '”' in author\
+                    #         or '大学' in author or '洛桑江村' in author:
                     #     continue
+                    if '国资委党委' in author:
+                        pass
+                    else:
+                        continue
                     new_href = new.find('a')['href']
                     is_member = r.sismember('qiushileaderspeech_two::' + period_title, new_href)
                     if is_member:

百度采集/baidu_comm/test.py

-# from baiduSpider import BaiduSpider
-# from baiduSpider import BaiduSpider
-# searchkw, wordsCode, sid = '', '', ''
-# baidu = BaiduSpider(searchkw, wordsCode, sid)
+from baiduSpider import BaiduSpider
+from baiduSpider import BaiduSpider
+searchkw, wordsCode, sid = '', '', ''
+baidu = BaiduSpider(searchkw, wordsCode, sid)
 import requests
 # url = 'https://baijiahao.baidu.com/s?id=1784907851792547880&wfr=spider&for=pc'
-# title = '“一带一路”商学院联盟副秘书长解奕炯：临沂在国际化物流建设中一定能“先行一步”'
-# try:
-#     detailurl = url
-#     title = title
-#     content, contentWithTag = baidu.extractorMsg(detailurl, title)
-#     contentWithTag = baidu.rmTagattr(contentWithTag, detailurl)
-# except Exception as e:
-#     content = ''
-#     contentWithTag = ''
-#
-#
-# detailmsg = {
-#     'title': title,
-#     'detailurl': url,
-#     'content': content,
-#     'contentHtml': contentWithTag,
-# }
-# print(detailmsg)
-headers = {
-    'Accept': '*/*',
-    'Accept-Encoding': 'gzip, deflate, br',
-    'Accept-Language': 'zh-CN,zh-TW;q=0.9,zh;q=0.8',
-    'Cache-Control': 'no-cache',
-    'Connection': 'keep-alive',
-    'Host': 'search-api-web.eastmoney.com',
-    'Pragma': 'no-cache',
-    'Sec-Fetch-Dest': 'script',
-    'Sec-Fetch-Mode': 'no-cors',
-    'Sec-Fetch-Site': 'same-site',
-    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
-    'sec-ch-ua': '"Not_A Brand";v="8", "Chromium";v="120", "Microsoft Edge";v="120"',
-    'sec-ch-ua-mobile': '?0',
-    'sec-ch-ua-platform': '"Windows"'
-}
-url = 'https://search-api-web.eastmoney.com/search/jsonp?cb=jQuery35103326233792363984_1702455623969&param=%7B%22uid%22%3A%22%22%2C%22keyword%22%3A%22%E7%A7%91%E8%BE%BE%E8%87%AA%E6%8E%A7%22%2C%22type%22%3A%5B%22researchReport%22%5D%2C%22client%22%3A%22web%22%2C%22clientVersion%22%3A%22curr%22%2C%22clientType%22%3A%22web%22%2C%22param%22%3A%7B%22researchReport%22%3A%7B%22client%22%3A%22web%22%2C%22pageSize%22%3A10%2C%22pageIndex%22%3A1%7D%7D%7D&_=1702455623970'
-# res = requests.get(url).text[1:-1]
-res = requests.get(url=url, headers=headers)
+url = 'https://www.163.com/dy/article/IKD3M2P20514IPKH.html'
+title = '“一带一路”商学院联盟副秘书长解奕炯：临沂在国际化物流建设中一定能“先行一步”'
+try:
+    detailurl = url
+    title = title
+    content, contentWithTag = baidu.extractorMsg(detailurl, title)
+    contentWithTag = baidu.rmTagattr(contentWithTag, detailurl)
+except Exception as e:
+    content = ''
+    contentWithTag = ''
 
-res_json = res.text
-print(res_json)
+
+detailmsg = {
\ No newline at end of file
+    'title': title,
+    'detailurl': url,
+    'content': content,
+    'contentHtml': contentWithTag,
+}
+print(detailmsg)
+# headers = {
+#     'Accept': '*/*',
+#     'Accept-Encoding': 'gzip, deflate, br',
+#     'Accept-Language': 'zh-CN,zh-TW;q=0.9,zh;q=0.8',
+#     'Cache-Control': 'no-cache',
+#     'Connection': 'keep-alive',
+#     'Host': 'search-api-web.eastmoney.com',
+#     'Pragma': 'no-cache',
+#     'Sec-Fetch-Dest': 'script',
+#     'Sec-Fetch-Mode': 'no-cors',
+#     'Sec-Fetch-Site': 'same-site',
+#     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+#     'sec-ch-ua': '"Not_A Brand";v="8", "Chromium";v="120", "Microsoft Edge";v="120"',
+#     'sec-ch-ua-mobile': '?0',
+#     'sec-ch-ua-platform': '"Windows"'
+# }
+# url = 'https://search-api-web.eastmoney.com/search/jsonp?cb=jQuery35103326233792363984_1702455623969&param=%7B%22uid%22%3A%22%22%2C%22keyword%22%3A%22%E7%A7%91%E8%BE%BE%E8%87%AA%E6%8E%A7%22%2C%22type%22%3A%5B%22researchReport%22%5D%2C%22client%22%3A%22web%22%2C%22clientVersion%22%3A%22curr%22%2C%22clientType%22%3A%22web%22%2C%22param%22%3A%7B%22researchReport%22%3A%7B%22client%22%3A%22web%22%2C%22pageSize%22%3A10%2C%22pageIndex%22%3A1%7D%7D%7D&_=1702455623970'
+# # res = requests.get(url).text[1:-1]
+# res = requests.get(url=url, headers=headers)
+#
+# res_json = res.text
+# print(res_json)
\ No newline at end of file