爬虫练手小项目:豆瓣高分图书TOP100
import requests
import re
from requests.exceptions import RequestException
import json
import time
def get_one_page(url):
headers ={
'User-Agent':'Mozilla/5.0 (Macintosh;Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36'}
response = requests.get(url,headers=headers)
if response.status_code == 200:
return response.text
return None
def parse_one_page(html,offset):
pattern = re.compile('<div.*?post.*?img.*?src="(.*?)".*?</div>.*?title.*?_blank">(.*?)</a>.*?rating_n