Created
October 2, 2011 12:37
-
-
Save anonymous/1257408 to your computer and use it in GitHub Desktop.
pydsnap
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
filter_nontrading_stocks = True | |
scraper = DsebdIntradayScraper(raw_html) | |
quotes = scraper.execute(filter_nontrading_stocks) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
# | |
# dse_intraday.py | |
# | |
# This file is part of the MaxTrader Project. http://www.maxtraderbd.com/ | |
# | |
# Copyright (c) 2011 invarBrass <NO_SPAM@maxtraderbd.com> | |
# Portions Copyright (c) 2010, M. Nasimul Haque | |
# | |
# All rights reserved. | |
# | |
# Redistribution and use in source and binary forms, with or without | |
# modification, are permitted provided that the following conditions are met: | |
# * Redistributions of source code must retain the above copyright | |
# notice, this list of conditions and the following disclaimer. | |
# * Redistributions in binary form must reproduce the above copyright | |
# notice, this list of conditions and the following disclaimer in the | |
# documentation and/or other materials provided with the distribution. | |
# * Neither the name of the MaxTrader Software Services nor the | |
# names of its contributors may be used to endorse or promote products | |
# derived from this software without specific prior written permission. | |
# | |
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND | |
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED | |
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE | |
# DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY | |
# DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES | |
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; | |
# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND | |
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | |
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS | |
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
# | |
# $Author: NO_SPAM@maxtraderbd.com $ | |
# $Id: dse_intraday.py 22 2011-10-01 15:33:48Z NO_SPAM@maxtraderbd.com $ | |
# $Rev: 22 $ | |
import re, string | |
from BeautifulSoup import BeautifulSoup | |
from pipeline import * | |
TICKER, LTP, HIGH, LOW, CLOSE, YCP, CHANGE, TRADE, VOLUME = range(1, 10) | |
class DseScraperContext(PipelineContext): | |
def __init__(self, raw_data): | |
self.raw_data = raw_data | |
self.sanitized_data = raw_data | |
self.filter_nontraded_stocks = True | |
def reset(self): | |
self.nontraded_stocks = 0 | |
self.raw_quotes = [] | |
self.validated_quotes = [] | |
self.table_rows = [] | |
self.soup = None | |
self.column_indices = {} | |
for i in range(TICKER, VOLUME + 1): | |
self.column_indices[i] = -1 | |
class HtmlSanitizationStage(Stage): | |
_tidy_patterns = { | |
'<body>': re.compile(r'<body[^>]*>', re.I), | |
'<tr>': re.compile(r'<tr[^>]*>', re.I), | |
'<td>': re.compile(r'<td[^>]*>', re.I), | |
'<a href="#">': re.compile(r'<a\s+href=[^>]*>', re.I), | |
'<font>': re.compile(r'<font[^>]*>', re.I), | |
'<!-- # -->': re.compile(r'<link[^>]*>', re.I), | |
' ': re.compile(r'[\r\n]') | |
} | |
def execute(self, context): | |
html = context.raw_data | |
for tag, rx in self._tidy_patterns.items(): | |
html = rx.sub(tag, html) | |
context.sanitized_data = html | |
#html = "".join([s for s in html.splitlines() if s.strip()]) | |
#tidy = lambda s: string.join(filter(string.strip, re.split(r'[\r\n]+', s)), '\n') | |
#html = tidy(html) | |
class SoupifyStage(Stage): | |
def execute(self, context): | |
context.reset() | |
context.soup = BeautifulSoup(context.sanitized_data) | |
context.table_rows = context.soup.body.table.findAll('tr') | |
class FieldsDiscoveryStage(Stage): | |
_column_patterns = { | |
TICKER: re.compile(r'\bcode\b', re.I), | |
LTP: re.compile(r'\bltp\b', re.I), | |
HIGH: re.compile(r'\bhigh\b', re.I), | |
LOW: re.compile(r'\blow\b', re.I), | |
CLOSE: re.compile(r'\bclose\b', re.I), | |
YCP: re.compile(r'\bycp\b', re.I), | |
CHANGE: re.compile(r'\bchange\b', re.I), | |
TRADE: re.compile(r'\btrade\b', re.I), | |
VOLUME: re.compile(r'\bvolume\b', re.I) | |
} | |
def execute(self, context): | |
header_row = context.table_rows[0] | |
cells = header_row.findAll('b') #.findAll('b') | |
for col_ix, cell in enumerate(cells): | |
vv = str(cell.contents[0]) | |
text = cell.find(text=True) | |
for i in range(TICKER, VOLUME + 1): | |
if self._column_patterns[i].search(text) != None: | |
context.column_indices[i] = col_ix + 1 | |
break | |
class QuotesScrapingStage(Stage): | |
def execute(self, context): | |
rows = context.table_rows[1:] | |
for row in rows: | |
cells = row.findAll('td') #[1:] | |
quote = {} | |
for field, index in context.column_indices.items(): | |
if field == TICKER: | |
quote[field] = cells[index].a.contents[0].strip() | |
else: | |
quote[field] = str(cells[index].find(text=True)).strip() | |
context.raw_quotes.append(quote) | |
class QuotesValidationStage(Stage): | |
def _sanitize(self, quote): | |
result = {} | |
for i in range(TICKER, VOLUME + 1): | |
if i == TICKER: | |
result[i] = quote[i].upper() | |
elif i >= LTP and i <= CHANGE: | |
value = float(quote[i]) | |
if i != CHANGE: | |
value = value if value >= 0 else 0 | |
result[i] = value | |
else: | |
value = int(quote[i]) | |
result[i] = value if value >= 0 else 0 | |
return result | |
def execute(self, context): | |
validated_quotes = [] | |
for quote in context.raw_quotes: | |
quote = self._sanitize(quote) | |
if (quote[TRADE] == 0) and context.filter_nontraded_stocks: | |
context.nontraded_stocks += 1 | |
else: | |
validated_quotes.append(quote) | |
context.validated_quotes = validated_quotes | |
class DsebdIntradayScraper(object): | |
__pipeline = None | |
def __init__(self): | |
self.__pipeline = SequentialPipeline() | |
self.__pipeline.add_stage(HtmlSanitizationStage()) | |
self.__pipeline.add_stage(SoupifyStage()) | |
self.__pipeline.add_stage(FieldsDiscoveryStage()) | |
self.__pipeline.add_stage(QuotesScrapingStage()) | |
self.__pipeline.add_stage(QuotesValidationStage()) | |
def execute(self, html, filter_nontraded_stocks = False): | |
context = DseScraperContext(html) | |
context.filter_nontraded_stocks = filter_nontraded_stocks | |
self.__pipeline.execute(context) | |
if context.has_errors(): | |
raise Exception(context.error_messages()) | |
return context.validated_quotes |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
# | |
# pipeline.py | |
# | |
# This file is part of the MaxTrader Project. http://www.maxtraderbd.com/ | |
# | |
# Copyright (c) 2011 invarBrass <NO_SPAM@maxtraderbd.com> | |
# | |
# All rights reserved. | |
# | |
# Redistribution and use in source and binary forms, with or without | |
# modification, are permitted provided that the following conditions are met: | |
# * Redistributions of source code must retain the above copyright | |
# notice, this list of conditions and the following disclaimer. | |
# * Redistributions in binary form must reproduce the above copyright | |
# notice, this list of conditions and the following disclaimer in the | |
# documentation and/or other materials provided with the distribution. | |
# * Neither the name of the MaxTrader Software Services nor the | |
# names of its contributors may be used to endorse or promote products | |
# derived from this software without specific prior written permission. | |
# | |
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND | |
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED | |
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE | |
# DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY | |
# DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES | |
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; | |
# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND | |
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | |
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS | |
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
# | |
# $Author: NO_SPAM@maxtraderbd.com $ | |
# $Id: pipeline.py 22 2011-10-01 15:33:48Z NO_SPAM@maxtraderbd.com $ | |
# $Rev: 22 $ | |
class PipelineContext(object): | |
_errors = [] | |
def get_errors(self): | |
return self._errors | |
def has_errors(self): | |
return True if len(self._errors) > 0 else False | |
def add_error(self, err): | |
self._errors.append(err) | |
def error_messages(self): | |
return '\r\n'.join(self._errors) | |
class Stage(object): | |
def execute(self, context): abstract | |
class Pipeline(Stage): | |
def add_stage(self, stage): abstract | |
class SequentialPipeline(Pipeline): | |
_stages = [] | |
def add_stage(self, stage): | |
self._stages.append(stage) | |
def execute(self, context): | |
for stage in self._stages: | |
stage.execute(context) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment