爬取中国大学排名并以csv格式存储
import requests
from bs4 import BeautifulSoup
import bs4
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 getUnivList(html):
"""解析页面内容,需要获取:学校排名,学校名称,省份,总分"""
soup = BeautifulSoup(html, 'lxml')
# 该页面只有一个表格,也只有一个tbody标签;
# 获取tbosy里面的所有子标签,返回的是生成器: soup.find('tb