菜鸡爬虫入门——爬取全国大学排名
作者:互联网
思路:
1.先获得url链接的html
2.再用BeautifulSoup库将html解析,在tbody中寻找tr,其中利用isinstance函数把不是标签类型的给剔除,然后把td存放到ulist列表里
3将ulist列表打印出来
三步思路对应着三个函数
代码:
import requests
from bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
try:
r=requests.get(url)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
print("错误")
def fillUnivList(ulist,html):
soup=BeautifulSoup(html,"html.parser")
for tr in soup.find('tbody').children:
if isinstance(tr,bs4.element.Tag):
tds=tr('td')
ulist.append([tds[0].string,tds[1].string,tds[3].string])
def printUnivList(ulist,num):
tplt = "{0:<10}\t{1:<69}\t{2:{3}^20}"
print("{0:<10}\t{1:<68}\t{2:{3}^20}".format("排名","学校名称","总分",chr(12288)))
for i in range(num):
u = ulist[i]
print(tplt.format(u[0],u[1],u[2],chr(12288)))
def main():
uinfo=[]
url="https://m.university-list.net/paiming/dx-160001.html"
html=getHTMLText(url)
fillUnivList(uinfo,html)
printUnivList(uinfo,20)
main()
结果:
标签:string,大学排名,tr,爬取,tds,bs4,html,菜鸡,ulist 来源: https://blog.csdn.net/dsp1234566/article/details/113539056