亞馬遜蘋果手機相關信息爬取 import re from bs4 import BeautifulSoup import time import requests amazon_url = 'https://www.amazon.cn/s/ref=sr_pg_2?rh=n%3A664978051%2Cn%3A665002051%2Ck%3Aiphone&page=1&bbn=665002051&keywords=iphone&ie=UTF8&qid=1523800289' def get_page_num(url):'''此函數用來要爬取總獲頁面數'''user_agent = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)\Chrome/64.0.3282.186 Safari/537.36'headers = {'User-Agent':user_agent}#這是頭信息，偽裝爬蟲res = requests.get(url,headers=headers)soup = BeautifulSoup(res.text,'lxml')page_num = soup.find('span',{'class':'pagnDisabled'}).get_text()return page_num def save_data(title,price): '''爬取的數據保存為文本格式'''with open('{}.txt'.format(time.strftime('%Y_%m_%d',time.localtime(time.time()))),'a') as f:#time.time()當前時間秒數#localtime（）時間秒數轉化為時間元祖#time.strftime()，時間元祖格式為字符串f.write(title + '\t' + price + '\n') def down_data(page_num):for i in range(1,int(page_num)+1):url = 'https://www.amazon.cn/s/ref=sr_pg_2?rh=n%3A664978051%2Cn%3A665002051%2Ck%3Aiphone\&page={}&bbn=665002051&keywords=iphone&ie=UTF8&qid=1523800289'.format(i)user_agent = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)\Chrome/64.0.3282.186 Safari/537.36'headers = {'User-Agent':user_agent}#這是頭信息，偽裝爬蟲res = requests.get(url,headers=headers)soup = BeautifulSoup(res.text,'lxml')titles = soup.find_all('h2',{'class':'a-size-base'})prices = soup.find_all('span',{'class':'a-size-base a-color-price s-price a-text-bold'})for i,j in zip(titles,prices):save_data(i.text,j.text) if __name__ == '__main__':page_num = get_page_num(url)down_data(page_num)

總結

以上是生活随笔為你收集整理的亚马逊苹果手机数据爬取的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。