获取天弘基金以及华夏基金最近5天收益信息

crawl.py

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import re
import requests

class Spider(object):
    def __init__(self, url, pattern, encoding):
        self.url = url
        self.pattern = pattern
        self.encoding = encoding
        
    def crawl(self):
        r = requests.get(self.url)
        if r.status_code != 200:
            print('HTTP error({})!'.format(r.status_code))
            return

        r.encoding = self.encoding
        return self.pattern.findall(r.text)

th_re = re.compile(r'''<tr>.+?
    <td>(\d+-\d+-\d+)</td>.+?
    <td>([\d.]+?)</td>.+?
    <td>([\d.]+?)%</td>.+?
    </tr>''', re.S|re.X)

tianhong = ['http://www.thfund.com.cn/website/hd/zlb/newzlbrev2.jsp', th_re, 'utf-8']

hx_re = re.compile(r'''<tr.+?>.+?
    <td.+?>(\d+-\d+-\d+)</td>.+?
    <td.+?>([\d.]+?)</td>.+?
    <td.+?>([\d.]+?)</td>.+?
    <td.+?>.+?</td>.+?
    <td.+?>.+?</td>.+?
    </tr>''', re.S|re.X)

huaxia = ['http://www.chinaamc.com/fund/003003/index.shtml', hx_re, 'gb2312']

if __name__ == '__main__':
    import colorit

    hx = Spider(*huaxia).crawl()[:5]
    th = Spider(*tianhong).crawl()[:5]

    green = colorit.paint('green')
    red = colorit.paint('red')

    print('{} {}'.format(green('huaxia'), red('tianhong')))
    for i in range(5):
        print('{} {}|{} {}|{}'.format(hx[i][0], green(hx[i][1]), red(th[i][1]), green(hx[i][2]), red(th[i][2])))