爬虫作业 

import requests
r=requests.get("http://www.baidu.com",timeout=30)
r.encoding='utf-8'
r.raise_for_status()
for i in range(20):
    print(i)
    print("函数测试输出:\n",r.text)
    n=len(r.text)
    m=len(r.content)
    print("text属性下网页长度为:{},content属性下网页长度为:{}".format(n,m))

　　

 

 

from bs4 import BeautifulSoup
html=BeautifulSoup("<!DOCTYPE html>\n<html>\n<head>\n<meta charset=‘utf-8‘>\n<title>菜鸟教程(runoob.com)</title>\n</head>\n<body>\n<h1>我的第一标题</h1>\n<p id=‘frist‘>我的第一段落。</p>\n</body>\n</table>\n</html>","html.parser")
print(html.head,"学号后两位：02")

　　

 

 

import re
r=html.text
pattern=re.findall(u'[\u1100-\uFFFDh]+?',r)
print(pattern)

　　

 

 

from bs4 import BeautifulSoup
import requests
allUniv=[]
def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return ""
def fillUnivList(soup):
    data = soup.find_all('tr')
    for tr in data:
        ltd = tr.find_all('td')
        if len(ltd)==0:
            continue
        singleUniv = []
        for td in ltd:
            singleUniv.append(td.string)
        allUniv.append(singleUniv)
def printUnivList(num):
    print("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^4}{5:{0}^10}".format((chr(12288)),"排名","学校名称","省市","总分","培训规模"))
    for i in range(num):
        u=allUniv[i]
        print("{1:^4}{2:{0}^10}{3:{0}^5}{4:{0}^8.1f}{5:{0}^10}".format((chr(12288)),u[0],u[1],u[2],eval(u[3]),u[6]))
def main(num):
    url='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2020.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(num)
main(10)

　　

posted @ 2020-12-13 21:51  dt_1005  阅读(91)  评论(0)    收藏  举报