python入门 访问网站并将爬回来的数据保存为csv文件

Posted 2020-12-22 树懒君

一、用requeses库的个体（）函数访问必应主页20次，打印返回状态，text内容，并且计算text（）属性和content属性返回网页内容的长度

代码如下：

 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))

运行结果如下：显示结果太多  这里只截一部分

 

二、爬取的2019年中国最好大学的排名（这里只显示排名前十的学校了）并且把它保存为csv文件

代码如下：

 1 import requests
 2 import csv
 3 import os
 4 import codecs
 5 from bs4 import BeautifulSoup
 6 allUniv = []
 7 def getHTMLText(url):
 8     try:
 9         r = requests.get(url, timeout=30)
10         r.raise_for_status()
11         r.encoding = \'utf-8\'
12         return r.text
13     except:
14         return ""
15 def fillUnivList(soup):
16     data = soup.find_all(\'tr\')
17     for tr in data:
18         ltd = tr.find_all(\'td\')
19         if len(ltd)==0:
20             continue
21         singleUniv = []
22         for td in ltd:
23             singleUniv.append(td.string)
24         allUniv.append(singleUniv)
25 def printUnivList(num):
26     print("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名称","省市","总分","培养规模"))
27     for i in range(num):
28         u=allUniv[i]
29         print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0],u[1],u[2],u[3],u[6]))
30 
31 def writercsv(save_road,num,title):
32     if os.path.isfile(save_road):
33         with open(save_road,\'a\',newline=\'\')as f:
34             csv_write=csv.writer(f,dialect=\'excel\')
35             for i in range(num):
36                 u=allUniv[i]
37                 csv_write.writerow(u)
38     else:
39          with open(save_road,\'w\',newline=\'\')as f:
40             csv_write=csv.writer(f,dialect=\'excel\')
41             csv_write.writerow(title)
42             for i in range(num):
43                 u=allUniv[i]
44                 csv_write.writerow(u)
45  
46 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"]
47 save_road="F:\\\\python\\csvData.csv"
48 def main():
49     url = \'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html\'
50     html = getHTMLText(url)
51     soup = BeautifulSoup(html, "html.parser")
52     fillUnivList(soup)
53     printUnivList(10)
54     writercsv(\'F:\\\\python\\csvData.csv\',10,title)
55 main()

代码显示结果如下：

打开文件: