一、爬取的網頁截圖

image.png

二、通過爬蟲生成的xlsx截圖

hahow課程網頁爬取ajax的接口處理數據后整理到xlsx中.png

三、代碼

import requests
import pandas as pd

# 設置url地址
url = "xxx"

# 設置headers模擬用戶端訪問接口
headers = {"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36"}

# 接收響應信息
response = requests.get(url, headers=headers)

# 處理數據
course_list = []
if response.status_code == 200:
    # 成功讀取網頁
    data = response.json()["data"]
    # print(data)
    for info in data:
        course_data = [
            info["title"],
            info["price"],
            info["averageRating"],
            info["numSoldTickets"]
        ]
        # 處理成這種是因為pandas需要列表
        course_list.append(course_data)
    # 寫入xlsx表格中
    pf = pd.DataFrame(course_list, columns=["課程標題","課程價格","課程評分","課程售賣數量"])
    pf.to_excel("new_course.xlsx", index = False, engine="openpyxl")
    print("Save!")
else:
    print("網頁讀取失敗")