融资融券获取所有排行

最新推荐文章于 2022-05-30 21:43:29 发布

回到未来望过去

最新推荐文章于 2022-05-30 21:43:29 发布

阅读量433

点赞数

文章标签： Python爬虫 BeautifulSoup 融资融券数据 CSV文件数据抓取

本文链接：https://blog.csdn.net/viviliving/article/details/119409841

版权

# -*- coding:utf-8 -*-             #不加这个报错
import requests
from bs4 import  BeautifulSoup
import  re
import  csv
import datetime

# http://data.10jqka.com.cn/market/rzrqgg/code/000400/

today = datetime.date.today().strftime('%Y%m%d')    #采集日期

Cookie = "Hm_lvt_60bad21af9c824a4a0530d5dbf4357ca=1587644691; Hm_lvt_f79b64788a4e377c608617fba4c736e2=1587644692; Hm_lvt_78c58f01938e4d85eaf619eae71b4ed1=1587644692; Hm_lpvt_f79b64788a4e377c608617fba4c736e2=1587644737; Hm_lpvt_60bad21af9c824a4a0530d5dbf4357ca=1587644737; Hm_lpvt_78c58f01938e4d85eaf619eae71b4ed1=1587644737; v=AmU_JzrXV8VWALMZXrG3U_-tdCqcohk0Y1b9iGdKIRyrfotcL_IpBPOmDVT0"
url = "https://data.10jqka.com.cn/market/rzrq/page/%d/"

headers = {
    'User-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.113 Safari/537.36',
    'Cookie': Cookie,
    'Connection': 'keep-alive',
    'Accept': '*/*',
    'Accept-Encoding': 'gzip, deflate',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Host': 'data.10jqka.com.cn',
    # 'Referer': 'http://www.sse.com.cn/market/stockdata/overview/weekly/'
}
#文件放在循环外打开，如果放在内部，那么前一次循环的数据会被覆盖掉
f = open('rzrq.csv', 'w', newline="")
writer = csv.writer(f)
# writer.writerow(('交易日期','本日融资余额(亿元)上海', '本日融资余额(亿元)深圳', '本日融资余额(亿元)沪深合计', '本日融资买入额(亿元)上海', '本日融资买入额(亿元)深圳', '本日融资买入额(亿元)沪深合计','本日融券余量余额(亿元)上海', '本日融券余量余额(亿元)深圳', '本日融券余量余额(亿元)沪深合计','本日融资融券余额(亿元)上海', '本日融资融券余额(亿元)深圳', '本日融资融券余额(亿元)沪深合计','采集日期'))

for k in range(1, 5):
    req = requests.get(url%k,headers=headers)
    html = BeautifulSoup(req.text,'lxml')
    datahead = html.select('#J-ajax-main > table > thead')
    # data = html.select('#J-ajax-main > table > tbody')
    data =html.select('#J-ajax-main > table > tbody > tr > td.tr,#J-ajax-main > table > tbody > tr > td.tc.linkToGghq')
    data = str(data).replace('-','')
    datas = re.findall('(\d+.?\d\d)',data)
    exc = [datas[i:i+12] for i in range(0,len(datas),12)]
    for j in range(len(exc)):
        line = exc[j]
        line.append(today)                  #这里每一行追加采集日期
        writer.writerow(line)

f.close()