上传文件至 python

python/微博热搜.py

@@ -0,0 +1,37 @@
+import requests
+import pandas as pd
+import datetime
+
+
+browse_header = {
+    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36'
+}
+
+url = "https://weibo.com/ajax/side/hotSearch"
+
+res = requests.get(url, headers=browse_header).json()
+# 实时上升热点
+content_list = res['data']['realtime']
+title_list = []
+order_list = []
+score_list = []
+desc_list = []
+index = 0
+for content in content_list:
+    index += 1
+    order_list.append(content['rank'])
+    title_list.append(content['word'])
+    score_list.append(content['num'])
+    desc_list.append(content['note'])
+
+df = pd.DataFrame({
+    '热搜标题': title_list,
+    '热搜排名': order_list,
+    '热搜热度': score_list,
+    '描述': desc_list,
+})
+print(datetime.datetime.now())
+current_datetime = datetime.datetime.now()
+xdate=current_datetime.strftime("%Y-%m-%d-%H-%M-%S")
+df.to_excel(f'../数据汇总/微博/{xdate}微博热搜榜.xlsx', index=False)  # 保存结果数据
+

python/抖音热搜.py

@@ -0,0 +1,44 @@
+import requests
+import pandas as pd
+import datetime
+
+
+browse_header = {
+    "Accept": "application/json, text/plain, */*",
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.60 Safari/537.36",
+    "Host": "www.douyin.com",
+    "Referer": "https://www.douyin.com/discover",
+    "Cookie": "_xsrf=Pd0NpG6J8kZdHtzBVnNyQP1g0rO7NKeg; _zap=d7f27b9f-4fe3-4ef4-9376-df278af16940;"
+}
+
+url = "https://www.douyin.com/aweme/v1/web/hot/search/list/?device_platform=webapp&aid=6383&channel=channel_pc_web"
+
+res = requests.get(url, headers=browse_header).json()
+# 实时上升热点
+content_list = res['data']['word_list']
+title_list = []
+order_list = []
+score_list = []
+desc_list = []
+url_list = []
+index = 0
+for content in content_list:
+    index += 1
+    order_list.append(content['position'])
+    title_list.append(content['word'])
+    score_list.append(content['hot_value'])
+    desc_list.append(content['word'])
+    url_list.append(f"https://www.douyin.com/hot/{content['sentence_id']}")
+
+df = pd.DataFrame({
+    '热搜标题': title_list,
+    '热搜排名': order_list,
+    '热搜热度': score_list,
+    '描述': desc_list,
+    '链接地址': url_list
+})
+print(datetime.datetime.now())
+current_datetime = datetime.datetime.now()
+xdate=current_datetime.strftime("%Y-%m-%d-%H-%M-%S")
+df.to_excel(f'../数据汇总/抖音/{xdate}抖音热搜榜.xlsx', index=False)  # 保存结果数据
+

python/百度热搜.py

@@ -0,0 +1,34 @@
+import requests
+import pandas as pd
+import datetime
+
+
+browse_header = {
+    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36'
+}
+
+url = "https://tenapi.cn/v2/baiduhot"
+
+res = requests.get(url, headers=browse_header).json()
+# 实时上升热点
+content_list = res['data']
+title_list = []
+score_list = []
+desc_list = []
+index = 0
+for content in content_list:
+    index += 1
+    title_list.append(content['name'])
+    score_list.append(content['hot'])
+    desc_list.append(content['url'])
+
+df = pd.DataFrame({
+    '热搜标题': title_list,
+    '热搜热度': score_list,
+    '热搜链接': desc_list,
+})
+print(datetime.datetime.now())
+current_datetime = datetime.datetime.now()
+xdate=current_datetime.strftime("%Y-%m-%d-%H-%M-%S")
+df.to_excel(f'../数据汇总/百度/{xdate}百度热搜榜.xlsx', index=False)  # 保存结果数据
+