Python学爬虫的课程备忘

学习慕课网的北京理工大学的嵩天老师关于爬虫的授课，讲的非常好。为了帮自己整理知识，特意在此备忘。
爬取百度的首页

至于版权，那还是算嵩老师的。

#CrawUnivRankingB.py
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[3].string])
 
def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.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://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs
main()

#!/usr/bin/python
# -*- coding: <encoding name> -*-

import requests

def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return '网络错误'

if __name__ == '__main__':
    url = 'http://www.baidu.com'
    print(getHTMLText(url))