A Scraper for Shareholding Data (Shanghai)

sc.py

#!/bin/env python3
"""
Stock Connect Northbound Shareholding Search By Date - Shanghai Connect
"""

__copyright__ = "Copyright (C) 2017 Xiaoyu Wei"

__license__ = """
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
"""

import requests
import re
from bs4 import BeautifulSoup
import datetime


def download_shareholdings(day,
                           month,
                           year,
                           sort_method='default',
                           filename=None):

    if sort_method == 'default':
        sort_method = ''

    print('Downloading shareholdings data ', year, month, day, '..')

    # {{{ scraping data

    print('  Requesting data..')

    url = 'http://www.hkexnews.hk/sdw/search/mutualmarket.aspx'
    headers = {
        "User-Agent":
        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.120 Safari/537.36"
    }

    s = requests.Session()
    s.headers.update(headers)

    r = s.get(url)
    soup = BeautifulSoup(r.content, "html.parser")
    viewstate = soup.select("#__VIEWSTATE")[0]['value']
    eventvalidation = soup.select("#__EVENTVALIDATION")[0]['value']
    viewstategenerator = soup.select("#__VIEWSTATEGENERATOR")[0]['value']

    today = datetime.date.today()
    date = format(today.year, '04d') + format(today.month, '02d') + format(
        today.day, '02d')

    form_data = {
        '__EVENTVALIDATION': eventvalidation,
        '__VIEWSTATE': viewstate,
        '__VIEWSTATEGENERATOR': viewstategenerator,
        'today': date,
        'sortBy': sort_method,
        'alertMsg': '',
        'btnSearch.x': '39',
        'btnSearch.y': '3',
        'ddlShareholdingDay': format(day, '02d'),
        'ddlShareholdingMonth': format(month, '02d'),
        'ddlShareholdingYear': format(year, '04d')
    }

    r = s.post(url, data=form_data)
    dessert = BeautifulSoup(r.content, "html.parser")

    # }}}

    # {{{ post processing

    print('  Post-prcessing..')

    data = dessert.find_all('table', {'class':
                                      'result-table'})[0].find_all('tr')

    header = data[0].find_all('th')
    header_contents = [i.contents for i in header]
    keys = []
    for h in header_contents:
        key_comps = [str(s) for s in h]
        key = ''.join(key_comps).replace('\n', '').replace('\r', '').replace(
            '<br/>', ' ')
        key = re.sub(r'<img alt=.+>', '', key)
        key = key.rstrip().lstrip()
        keys.append(key)

    values = []
    # skip a blank tr
    for row in data[2:]:
        cols = row.find_all('td')
        col_contents = [
            ''.join(i.contents).replace('\n', '').replace('\r',
                                                          '').lstrip().rstrip()
            for i in cols
        ]
        values.append(col_contents)

    # cleaning figures
    for val in values:
        val[1] = '"' + val[1] + '"'
        val[2] = val[2].replace(',', '')
        val[3] = val[3].replace('%', '')
        for vv in val:
            vv = vv.rstrip().lstrip()

    # extract actual shareholding date
    hold_date = ''.join(
        dessert.find("div", {"id": "pnlResult"}).findChildren()[0]
        .contents).replace('\n', '').replace(
            '\r', '').lstrip().rstrip().split(' ')[-1]
    # print('  Actual shareholding date:', hold_date)
    hold_day, hold_month, hold_year = hold_date.split('/')

    # output filename
    if filename == None or len(filename) == 0:
        csv_filename = 'shareholdings-' + hold_year + hold_month + hold_day + '-sorted_by_' + sort_method + '.csv'
    else:
        csv_filename = filename

    print('  Output written in', csv_filename)

    # dump into a csv
    f = open(csv_filename, 'w')
    for i in range(len(keys)):
        f.write(keys[i])
        if i < len(keys) - 1:
            f.write(',')
        else:
            f.write('\n')
    for r in values:
        for j in range(len(r)):
            f.write(r[j])
            if j < len(r) - 1:
                f.write(',')
            else:
                f.write('\n')
    f.close()


# }}}

# vim: fdm=marker

scraper_demo.py

#!/bin/env python3

import sc

# query info
days = [5, 10, 15, 20]
month = 10
year = 2017

# optional
# other options are: stockcode, stockname, Shareholding, ShareholdingPercent
sort_method = 'default'

# optional, set None to use auto-generated filename
output_filename = None

for day in days:
    sc.download_shareholdings(day, month, year, sort_method, output_filename)
print('Done.')