简单实现查找历史说说并导出为excel

main.py

@@ -2,12 +2,19 @@ from bs4 import BeautifulSoup
 from tqdm import trange
 import util.RequestUtil as Request
 import util.ToolsUtil as Tools
+import util.ConfigUtil as Config
 import pandas as pd
+
 if __name__ == '__main__':
+    user_info = Request.get_login_user_info()
+    user_nickname = user_info[Request.uin][6]
+    print(f"用户<{Request.uin}>,<{user_nickname}>登录成功")
     texts = []
-    for i in trange(2, desc='Progress', unit='iteration'):
-        message = Request.get_message(i*100, 100).content.decode('utf-8')
+    for i in trange(1000, desc='Progress', unit='iteration'):
+        message = Request.get_message(i * 100, 100).content.decode('utf-8')
         html = Tools.process_old_html(message)
+        if "li" not in html:
+            break
         soup = BeautifulSoup(html, 'html.parser')
         for element in soup.find_all('p', class_='txt-box-title ellipsis-one'):
             text = element.get_text().replace('\xa0', ' ')
@@ -16,6 +23,6 @@ if __name__ == '__main__':
     # 创建一个DataFrame对象
     df = pd.DataFrame(texts, columns=['内容'])
 
-    # 将DataFrame对象导出为CSV文件，使用UTF-8编码
-    df.to_excel('output.xlsx', index=False)
-    print(texts)
+    # 导出为Excel
+    df.to_excel(Config.result_path + Request.uin + '.xlsx', index=False)
+    print('导出成功,请查看 ' + Config.result_path + Request.uin + '.xlsx')

resource/config/config.ini

@@ -1,3 +1,4 @@
 [File]
 temp = ./resource/temp/
-user = ./resource/user/
+user = ./resource/user/
+result = ./resource/result/

util/ConfigUtil.py

@@ -6,6 +6,7 @@ config.read('./resource/config/config.ini')
 
 temp_path = config.get('File', 'temp')
 user_path = config.get('File', 'user')
+result_path = config.get('File', 'result')
 
 
 def save_user(cookies):

util/LoginUtil.py

@@ -2,9 +2,9 @@ import requests
 from PIL import Image
 import time
 import re
-import os
 import util.ConfigUtil as Config
 
+
 def bkn(pSkey):
     # 计算bkn
     t, n, o = 5381, 0, len(pSkey)

util/RequestUtil.py

@@ -1,6 +1,6 @@
 import util.LoginUtil as Login
 import requests
-
+import json
 # 登陆后获取到的cookies
 cookies = Login.cookie()
 # 获取g_tk
@@ -52,3 +52,12 @@ def get_message(start, count):
     response = requests.get('https://user.qzone.qq.com/proxy/domain/ic2.qzone.qq.com/cgi-bin/feeds/feeds2_html_pav_all',
                             params=params, cookies=cookies, headers=headers)
     return response
+
+
+def get_login_user_info():
+    response = requests.get('https://r.qzone.qq.com/fcg-bin/cgi_get_portrait.fcg?g_tk=' + str(g_tk) + '&uins=' + uin,
+                            headers=headers, cookies=cookies)
+    info = response.content.decode('GBK')
+    info = info.strip().lstrip('portraitCallBack(').rstrip(');')
+    info = json.loads(info)
+    return info

util/ToolsUtil.py

@@ -25,7 +25,7 @@ def process_old_html(message):
 
     new_text = re.sub(r'\\x[0-9a-fA-F]{2}', replace_hex, message)
     start_string = "html:'"
-    end_string = "\'\,opuin"
+    end_string = "',opuin"
     new_text = extract_string_between(new_text, start_string, end_string)
     new_text = replace_multiple_spaces(new_text).replace('\\', '')
     return new_text