python爬取大学排名
发布时间
阅读量：
阅读量
返回加载出来的数据
def getHTMLText(url):
return ""
解析列表
def fillUnivList(ulist, html):
pass
打印数据
def printUnivList(ulist, num):
pass
进行调用函数，返回结果
def main():
unifo = []
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
# 加载html
html = getHTMLText(url)
# 解析html,返回列表
fillUnivList(unifo, html)
printUnivList(unifo, 20)
main()
代码解读getHTMLText函数代码如下：
def getHTMLText(url):
try:
r = requests.get(url, timeout=30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ""
代码解读fillUnivList代码如下, 过滤不是tr的标签，找到tr下的td下的三行
def fillUnivList(ulist, html):
soup = BeautifulSoup(html, "html.parser")
for tr in soup.find('tbody').children:
# 过滤
if isinstance(tr, bs4.element.Tag):
tds = tr('td')
ulist.append([tds[0].string, tds[1].string, tds[2].string])
代码解读printUnivList代码如下，遍历前二十列数据，汉字是另一种编码
def printUnivList(ulist, num):
# 位置，补数字，约束几个字符
tplt = "{0:^5}\t{1:{3}^10}\t{2:^4}"
print(tplt.format("排名", "学校", "总分", chr(12288)))
for i in range(num):
u = ulist[i]
print(tplt.format(u[0], u[1], u[2], chr(12288)))
代码解读整体代码如下：
import bs4
import requests
from bs4 import BeautifulSoup
def getHTMLText(url):
try:
r = requests.get(url, timeout=30)
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:
# 过滤
if isinstance(tr, bs4.element.Tag):
tds = tr('td')
ulist.append([tds[0].string, tds[1].string, tds[2].string])
def printUnivList(ulist, num):
# 位置，补数字，约束几个字符
tplt = "{0:^5}\t{1:{3}^10}\t{2:^4}"
print(tplt.format("排名", "学校", "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():
unifo = []
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
# 加载html
html = getHTMLText(url)
# 解析html,返回列表
fillUnivList(unifo, html)
printUnivList(unifo, 20)
main()
代码解读全部评论 (0)
还没有任何评论哟~