要求:
url = “http://movie.douban.com/top250/”
需要获取的信息: 电影名称, 电影评分, 评价人数, 电影短评
import re
import requests
from bs4 import BeautifulSoup
def get_content(url,):
try:
user_agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.109 Safari/537.36"
response = requests.get(url, headers={'User-Agent': user_agent})
response.raise_for_status() # 如果返回的状态码不是200, 则抛出异常;
response.encoding = response.apparent_encoding # 判断网页的编码格式, 便于respons.text知道如何解码;
except Exception as e:
print("爬取错误")
else:
print(response.url)
print("爬取成功!")
return response.content
def parser_content(htmlContent):
# 实例化soup对象, 便于处理;
soup = BeautifulSoup(htmlContent, 'html.parser&#