爬取编程语言排名
技术路线
思路分析
代码实现
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:
return ""
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):
tplr = "{0:^10}\t{1:^10}\t{2:^10}"
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
print(tplr.format("2021排名","2020排名","编程语言",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://www.tiobe.com/tiobe-index/'
html = getHTMLText(url)
fillUnivList(uinfo,html)
printUnivList(uinfo,10)
main()