已经抓取新浪的数据
和讯网的怎么抓取数据 所传的参数是怎么样的
解决问题采纳答案 谢谢 速来
是调用别人正规暴露的接口,还是爬虫爬数据啊
和讯网查看数据的地址发一下
是和讯网提供的获取数据的接口吗
新浪有公共的对外接口,和讯网就不知道了
和讯网债券数据Python爬取保存成CSV文件之一
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,
tds[8].string, tds[9].string, tds[10].string])
return bondlist
def write_csv(data):
# 1.创建指定文件夹
path = r'F:\Bond'
if not os.path.exists('F:/Bond'):
os.mkdir(path)
os.chdir(path)
# 2.创建文件对象,并以日期命名文件
f = open(datetime.now().date().isoformat()+'国债基金.csv', 'w', encoding='utf-8-sig', newline='')
# 3. 基于文件对象构建 csv写入对象
csv_writer = csv.writer(f)
# 4. 构建列表头
csv_writer.writerow(["代码","简称","全价","年利率","期限","剩余期限",
"净价","应计天数","应计利息","付息方式","到期收益率"])
# 5. 写入csv文件内容
for dat in data:
csv_writer.writerow(dat)
# 6. 关闭文件
f.close()
def main():
url = "http://bond.money.hexun.com/data/bond_nationaldebt_list.htm"
bondlist = []
html = getHtml(url)
data = getBondlist(bondlist,html)
write_csv(data)
main()
用excel打开后格式如下图所示
可以参考如下链接https://blog.csdn.net/weixin_43025064/article/details/122817534