import requests
import pandas as pd
def fetch_ajax_data(page):
    url = "https://example.com/api/products"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
        "Referer": "https://example.com/products",
    }
    params = {
        "page": page,
        "size": 10,
    }
    response = requests.get(url, headers=headers, params=params)
    if response.status_code == 200:
        return response.json()  # 假設(shè)返回的是JSON數(shù)據(jù)
    else:
        print(f"請(qǐng)求失敗，狀態(tài)碼：{response.status_code}")
        return None

def crawl_ajax_pages(max_pages=5):
    all_products = []
    for page in range(1, max_pages + 1):
        print(f"正在爬取第 {page} 頁(yè)...")
        data = fetch_ajax_data(page)
        if data and "products" in data:
            all_products.extend(data["products"])
        else:
            print(f"第 {page} 頁(yè)無(wú)數(shù)據(jù)或解析失敗")
    return all_products

def save_to_csv(data, filename="products.csv"):
    df = pd.DataFrame(data)
    df.to_csv(filename, index=False, encoding="utf-8-sig")
    print(f"數(shù)據(jù)已保存至 {filename}")
# 執(zhí)行爬取
if __name__ == "__main__":
    products = crawl_ajax_pages(max_pages=5)
    if products:
        save_to_csv(products)

import time
from fake_useragent import UserAgent
def fetch_ajax_data_safe(page):
    ua = UserAgent()
    headers = {
        "User-Agent": ua.random,
        "Referer": "https://example.com/products",
    }
    time.sleep(1)  # 避免請(qǐng)求過快
    # 其余代碼同上...

try:
    response = requests.get(url, headers=headers, params=params, timeout=10)
    response.raise_for_status()  # 檢查HTTP錯(cuò)誤
except requests.exceptions.RequestException as e:
    print(f"請(qǐng)求異常：{e}")
    return None

import requests
import pandas as pd
import time
from fake_useragent import UserAgent
# 代理服務(wù)器配置
proxyHost = "www.16yun.cn"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"
# 構(gòu)造代理字典
proxies = {
    "http": f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}",
    "https": f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}",
}
def fetch_ajax_data(page):
    ua = UserAgent()
    url = "https://example.com/api/products"
    headers = {
        "User-Agent": ua.random,
        "Referer": "https://example.com/products",
    }
    params = {
        "page": page,
        "size": 10,
    }
    try:
        time.sleep(1)  # 防止請(qǐng)求過快
        # 添加proxies參數(shù)使用代理
        response = requests.get(
            url,
            headers=headers,
            params=params,
            timeout=10,
            proxies=proxies
        )
        response.raise_for_status()
        return response.json()
    except requests.exceptions.RequestException as e:
        print(f"第 {page} 頁(yè)請(qǐng)求失敗：{e}")
        return None
def crawl_ajax_pages(max_pages=5):
    all_products = []
    for page in range(1, max_pages + 1):
        print(f"正在爬取第 {page} 頁(yè)...")
        data = fetch_ajax_data(page)
        if data and "products" in data:
            all_products.extend(data["products"])
        else:
            print(f"第 {page} 頁(yè)無(wú)數(shù)據(jù)或解析失敗")
    return all_products
def save_to_csv(data, filename="products.csv"):
    df = pd.DataFrame(data)
    df.to_csv(filename, index=False, encoding="utf-8-sig")
    print(f"數(shù)據(jù)已保存至 {filename}")
if __name__ == "__main__":
    products = crawl_ajax_pages(max_pages=5)
    if products:
        save_to_csv(products)