MOOC_北理_Python爬虫学习_5（大学排名爬虫）

这是一章实战。。然后看课程前尝试着能不能自己爬取，一番尝试下成功是成功了。
方法一：

import requests
from bs4 import BeautifulSoup
url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html"
html = requests.get(url)
html.encoding = html.apparent_encoding
txt = html.text
soup = BeautifulSoup(txt,"html.parser")
info = soup.find_all('tr','alt')

for i in range(50):
    print(info[i]('td')[0].string)
    print(info[i]('td')[2].string)
    print(info[i].div.string)

#info的类型是<class 'bs4.element.ResultSet'> Set，集合？所以可以索引？？（我猜）
#info[i]的类型是<class 'bs4.element.Tag'>标签，所以可以在后面加上啥string attrs啥的。

方法二：

import requests
from bs4 import BeautifulSoup
url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html"
html = requests.get(url)
html.encoding = html.apparent_encoding
txt = html.text
soup = BeautifulSoup(txt,"html.parser")
Univ_ls = []
for child in soup.tbody.children:
    Univ_ls.append(child)

for i in range(1,200):
    print(Univ_ls[i].div.string)

这里有个问题，就是最后的for i in range(1,200)必须要在1开始，这个列表的第0项是空，我也不知道为啥。。可能是设定源代码里第一个子节点为空？

方法三（课程中给出的代码）：

import requestsfrom bs4 
import BeautifulSoupimport 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()