第一个爬虫和测试

 1 import requests
 2 def getHTMLText(url):
 3     try:
 4         for i in range(0,20):                   #访问20次
 5             r = requests.get(url, timeout=30)
 6         r.raise_for_status() #如果状态不是200，引发异常
 7         r.encoding = ‘utf-8‘ #无论原来用什么编码，都改成utf-8
 8         return r.status_code,r.text,r.content,len(r.text),len(r.content)  ##返回状态，text和content内容，text（）和content（）网页的长度
 9     except:
10         return ""
11 url = "https://cn.bing.com/?toHttps=1&redig=731C98468AFA474D85AECB7DB98B95D9"
12 print(getHTMLText(url))

import requests
import csv
import os
import codecs
from bs4 import BeautifulSoup
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("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名称","省市","总分","培养规模"))
    for i in range(num):
        u=allUniv[i]
        print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0],u[1],u[2],u[3],u[6]))

def writercsv(save_road,num,title):
    if os.path.isfile(save_road):
        with open(save_road,‘a‘,newline=‘‘)as f:
            csv_write=csv.writer(f,dialect=‘excel‘)
            for i in range(num):
                u=allUniv[i]
                csv_write.writerow(u)
    else:
         with open(save_road,‘w‘,newline=‘‘)as f:
            csv_write=csv.writer(f,dialect=‘excel‘)
            csv_write.writerow(title)
            for i in range(num):
                u=allUniv[i]
                csv_write.writerow(u)

title=["排名","学校名称","省市","总分","生源质量","培养结果","科研规模","科研质量","顶尖成果","顶尖人才","科技服务","产学研究合作","成果转化"]
save_road="F:\\python\csvData.csv"
def main():
    url = ‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html‘
    html = getHTMLText(url)
    soup = BeautifulSoup(html, "html.parser")
    fillUnivList(soup)
    printUnivList(10)
    writercsv(‘F:\\python\csvData.csv‘,10,title)
main()