Beautiful Soup库

Beautiful Soup:解析HTML页面，信息标记与提取方法。
安装;

使用：

import requests
r=requests.get("http://python123.io/ws/demo.html")
r.text
demo=r.text
from bs4 import BeautifulSoup
soup=BeautifulSoup(demo,"html.parser")
print(soup.prettify())

结果：

Beautiful Soup库解析器;

Beautiful Soup类的基本元素


标签树的平行遍历：

bs4库的编码:

信息提取;

import requests
r=requests.get("http://python123.io/ws/demo.html")
r.text
demo=r.text
from bs4 import BeautifulSoup
soup=BeautifulSoup(demo,"html.parser")
for link in soup.find_all('a'):
    print(link.get('href'))

注：参数与find_all()一致。
爬取最好大学网排名：

import requests
from bs4 import BeautifulSoup
import bs4

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:
        if isinstance(tr,bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string,tds[1].string,tds[2].string])

def printUnivList(ulist,num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    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)))
# print("Suc" + str(num))


def main():
    uinfo = []
    url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo,20) # 20 unives
main()