python3实践-从网站获取数据(Carbon Market Data-GD) （bs4/Beautifulsoup）

 1 # Code based on Python 3.x
 2 # _*_ coding: utf-8 _*_
 3 # __Author: "LEMON"
 4 
 5 
 6 from bs4 import BeautifulSoup
 7 import requests
 8 import csv
 9 
10 url2 = ‘http://ets.cnemission.com/carbon/portalIndex/markethistory?Top=1‘
11 
12 req = requests.get(url2)
13 # soup = BeautifulSoup(req.content, ‘html5lib‘)
14 soup = BeautifulSoup(req.content, ‘lxml‘)
15 # 用“lxml”解析，可以获得数据，但csv文件中每行有空行
16 
17 table = soup.table
18 trs = table.find_all(‘tr‘)
19 
20 list1 = []
21 for tr in trs:
22     td = tr.find_all(‘td‘)
23 
24     # 去除每个单元格数据后面的"\r"和"\n"和"\t"，
25     # 下面两种方法都可以生成csv文件，
26     # 但method1生成的csv文件较小，应该是优化性能较好，暂时不明白其中原理
27     # method1
28     row = [i.text.replace(‘\r‘, ‘‘).replace(‘\n‘, ‘‘).replace(‘\t‘, ‘‘) for i in td]
29     # method 2
30     # row = [i.text.replace(‘\r\n\t‘, ‘‘) for i in td]
31 
32     list1.append(row)
33 
34 with open(‘MktDataGuangdong.csv‘, ‘a‘, errors=‘ignore‘, newline=‘‘) as f:
35     f_csv = csv.writer(f)
36     f_csv.writerows(list1)