亚马逊苹果手机相关信息爬取
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'
defget_page_num(url):'''此函数用来要爬取总获页面数'''
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}#这是头信息,伪装爬虫
res = requests.get(url,headers=headers)
soup = BeautifulSoup(res.text,'lxml')
page_num = soup.find('span',{'class':'pagnDisabled'}).get_text()
return page_num