python爬虫——大学排名

import requests
from bs4 import BeautifulSoup
ALL = []
def getHTMLtext(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return ""

def fillUni(soup):
    data = soup.find_all('tr')
    for tr in data:
        td1 = tr.find_all('td')
        if len(td1) == 0:
            continue
        Single = []
        for td in td1:
            Single.append(td.string)
        ALL.append(Single)

def printUni(num):
    print("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^6}{5:{0}^6}{6:{0}^6}{7:{0}^6}{8:{0}^6}{9:{0}^5}{10:{0}^6}{11:{0}^6}{12:{0}^6}{13:{0}^6}".format(chr(12288),"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"))
    for i in range(num):
          u = ALL[i]
          print("{1:^4}{2:{0}^10}{3:{0}^6}{4:{0}^8}{5:{0}^9}{6:{0}^9}{7:{0}^7}{8:{0}^9}{9:{0}^7}{10:{0}^9}{11:{0}^8}{12:{0}^9}{13:{0}^9}".format(chr(12288),u[0],\
                                                                                                                                                          u[1],u[2],eval(u[3]),\
                                                                                                                                                          u[4],u[5],u[6],u[7],u[8],\
                                                                                                                                                          u[9],u[10],u[11],u[12]))

def main(num):
          url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
          html = getHTMLtext(url)
          soup = BeautifulSoup(html,"html.parser")
          fillUni(soup)
          printUni(num)
 
import requests
from bs4 import BeautifulSoup
import csv
import os

ALL = []
def getHTMLtext(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return ""

def fillUni(soup):
    data = soup.find_all('tr')
    for tr in data:
        td1 = tr.find_all('td')
        if len(td1) == 0:
            continue
        Single = []
        for td in td1:
            Single.append(td.string)
        ALL.append(Single)
        

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=ALL[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=ALL[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="C:\\Users\\86138\\Desktop\\html.csv"

def main(num):
    url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    html = getHTMLtext(url)
    soup = BeautifulSoup(html,"html.parser")
    fillUni(soup)
    writercsv(save_road,num,title) 

main(10) 

标签：soup,python,html,爬虫,大学排名,num,url,csv,def
来源： https://www.cnblogs.com/leisure-yee/p/14128515.html