本文讲述国债数据使用python爬取的方式,并将得到的数据保存成CSV文件以日期命名,方便后期处理。
具体代码如下所示:
import requests
from bs4 import BeautifulSoup
import bs4
import csv
import os
from datetime import datetime
def getHtml(url):
try:
kv = {'user-agent': 'Mozilla/5.0'}
r = requests.get(url, headers = kv)
r.encoding = r.apparent_encoding
r.raise_for_status()
html = r.text
return html
except:
return "获取数据失败"
def getBondlist(bondlist, html):
soup = BeautifulSoup(html, "html.parser")
for tr in soup.find('tbody').children:
if isinstance(tr,bs4.element.Tag):
tds = tr('td')
bondlist.append([tds[0].string, tds[1].string, tds[2].string, tds[3].string,
tds[4].string, tds[5].string, tds[6].string, tds[7].string,