Beispiel #1
0
def get_sportcoat_measurements(html_description, parse_strategy='default'):
    """Parses a sportcoat listing from seller balearic1 and returns the measurements
	as a dict.

	Parameters
	----------
	html_description : str
	parse_strategy : str
		Defaults to 'default'

	Returns
	-------
	m : MeasurementsCollection instance
	"""

    soup = BeautifulSoup(html_description, 'html.parser')

    try:
        assert soup.find(string='Approximate Measurements') != None
    except AssertionError:
        raise UnrecognizedTemplateHTML(
            'Unable to find "Approximate Measurements" string in HTML description',
            html_string=str(soup))
    else:
        data = (
            soup.find(string='Approximate Measurements')  # string itself
            .parent  # enclosing <h3>
            .parent  # enclosing <td>
            .parent  # enclosing <tr>
            .parent  # enclosing <tbody>
            .parent  # enclosing <table>
        )

    m_list = []

    if parse_strategy == 'default':
        strings = list(data.stripped_strings)
        try:
            m_list.append(Msmt('jacket', 'chest_flat', str2int(strings[2])))
            m_list.append(Msmt('jacket', 'sleeve', str2int(strings[4])))
            m_list.append(Msmt('jacket', 'shoulders', str2int(strings[6])))
            m_list.append(Msmt('jacket', 'waist_flat', str2int(strings[8])))
            m_list.append(Msmt('jacket', 'length', str2int(strings[10])))
            # TypeError raised by Measurement class if passed non int value
            # as the measurement value
        except TypeError as e:
            raise UnrecognizedMeasurement(
                'Instantiation of Measurement class ({}) by parsing html raised a KeyError, \
				indicating the parser identified a region that it expected would be a \
				measurement value.'.format(e),
                html_string=str(data))
    else:
        raise UnsupportedParsingStrategy(
            'Parsing strategy <{}> is not supported for this category'.format(
                parse_strategy))
    m = MeasurementsCollection(parse_strategy=parse_strategy,
                               parse_html=str(data),
                               measurements_list=m_list)

    return m
def get_sportcoat_measurements(measurements_table_soup, parse_strategy='default'):
	"""Parses a sportcoat listing from seller balearic1 and returns the measurements
	as a dict.

	Parameters
	----------
	measurements_table_soup : BeautifulSoup instance
	parse_strategy='default' : str

	Returns
	-------
	m : MeasurementsCollection instance
	"""

	logger.debug('Attempting to parse as a sportcoat')

	if type(measurements_table_soup) is not BeautifulSoup:
		raise ValueError('Must be given a BeautifulSoup object')

	m_list = []

	if parse_strategy == 'default':
		logger.debug('Using parse_strategy={}'.format(parse_strategy))
		strings = list(measurements_table_soup.stripped_strings)
		try:
			m_list.append(Msmt('jacket', 'chest_flat', str2int(strings[2])))
			m_list.append(Msmt('jacket', 'sleeve', str2int(strings[4])))
			m_list.append(Msmt('jacket', 'shoulders', str2int(strings[6])))
			m_list.append(Msmt('jacket', 'waist_flat', str2int(strings[8])))
			m_list.append(Msmt('jacket', 'length', str2int(strings[10])))
			# TypeError raised by Measurement class if passed non int value
			# as the measurement value
		except TypeError as e:
			raise UnrecognizedMeasurement((
				'Instantiation of Measurement class ({}) by parsing html raised a KeyError, '
				'indicating the parser identified a region that it expected would be a '
				'measurement value.').format(e), html_string=str(measurements_table_soup))
		except IndexError:
			raise UnrecognizedTemplateHTML((
				'parse_strategy={} expected a differing number of measurements than '
				'what was provided by the template.').format(parse_strategy),
				html_string=str(data))
	else:
		raise UnsupportedParsingStrategy(
			'Parsing strategy <{}> is not supported for this category'.format(
				parse_strategy))
	m = MeasurementsCollection(
		parse_strategy=parse_strategy,
		parse_html=str(measurements_table_soup),
		measurements_list=m_list)

	return m
Beispiel #3
0
def test_parse_fn_finds_raglan(parse_fn, measurements_table_soup_raglan):
    raglan_jacket_parse = parse_fn(measurements_table_soup_raglan, 'default')
    measurements = raglan_jacket_parse.measurements_list
    # Check to see if these Measurement instances are in the measurements list
    assert any([
        measurement.__dict__ == Msmt('jacket', 'sleeve_from_armpit',
                                     19000).__dict__
        for measurement in measurements
    ]) is True
    assert any([
        measurement.__dict__ == Msmt('jacket', 'shoulders_raglan', 0).__dict__
        for measurement in measurements
    ]) is True
    # Check to be sure shoulders and normal sleeve measurements are NOT in the list
    assert any(
        [measurement.attribute == 'shoulders'
         for measurement in measurements]) is False
    assert any(
        [measurement.attribute == 'sleeve'
         for measurement in measurements]) is False
Beispiel #4
0
def dehydrated_ParseResult():
    p = ParseResult()
    p.clothing_type = 'pant'
    p.meta = {
        'parse_strategy':
        'default',
        'concerns': [],
        'parsed_html':
        '<table cellpadding="0" cellspacing="0" style="font-size: inherit; ">\n<tbody><tr><td class="head" colspan="2"><h3>Approximate Measurements</h3></td></tr>\n<tr>\n<td>Across Waist</td>\n<td>15”</td></tr><tr><td>Across Hips</td>\n<td>18"</td>\n</tr>\n<tr>\n<td>Inseam</td>\n<td>28.5”\xa0</td>\n</tr>\n<tr>\n<td>Cuff Height</td>\n<td>0"</td>\n</tr><tr>\n<td>Material underneath hem</td>\n<td>2.25"</td>\n</tr><tr>\n<td>Width of hem opening</td>\n<td>9"</td>\n</tr><tr>\n<td>Rise</td>\n<td>9.75"</td></tr>\n</tbody></table>'
    }
    p.measurements = [
        Msmt(category='pant', attribute='waist_flat', measurement_value=15000),
        Msmt(category='pant', attribute='hips_flat', measurement_value=18000),
        Msmt(category='pant', attribute='inseam', measurement_value=28500),
        Msmt(category='pant', attribute='cuff_height', measurement_value=0),
        Msmt(category='pant', attribute='cuff_width', measurement_value=9000),
        Msmt(category='pant', attribute='rise', measurement_value=9750)
    ]
    return p.json()
def get_sweater_measurements(measurements_table_soup, parse_strategy='default'):
	"""Parses a sweater listing from seller balearic1 and returns a
	MeasurementsCollection instance.

	parse_strategy='default' attempts to detect raglan shoulders and sleeves
	measured from underarm and act accordingly.
	accordingly.

	Parameters
	----------
	measurements_table_soup : BeautifulSoup instance
	parse_strategy='default' : str

	Returns
	-------
	m : MeasurementsCollection instance
	"""

	logger.debug('Attempting to parse as a sweater')

	if type(measurements_table_soup) is not BeautifulSoup:
		raise ValueError('Must be given a BeautifulSoup object')

	m_list = []

	if parse_strategy == 'default':
		logger.debug('Using parse_strategy={}'.format(parse_strategy))
		strings = list(measurements_table_soup.stripped_strings)
		sweater_uses_raglan = measurements_table_soup.find(
			string=re.compile('raglan', flags=re.IGNORECASE)) is not None
		sweater_uses_underarm = measurements_table_soup.find(
			string=re.compile('underarm', flags=re.IGNORECASE)) is not None

		if sweater_uses_raglan != sweater_uses_underarm:
			raise UnrecognizedTemplateHTML(
				'Expected template text search for "raglan" and "underarm" to BOTH == True\
				or BOTH == False. Found raglan={} and sweater_uses_underarm={}'.format(
					sweater_uses_raglan, sweater_uses_underarm),
				html_string=str(measurements_table_soup))

		strings = list(measurements_table_soup.stripped_strings)
		try:
			m_list.append(Msmt('sweater', 'chest_flat', str2int(strings[2])))
			m_list.append(Msmt('sweater', 'length', str2int(strings[8])))

			# Handle cases with raglan sleeves or not
			if sweater_uses_raglan and sweater_uses_underarm:
				m_list.append(Msmt('sweater', 'sleeve_from_armpit', str2int(strings[4])))
				m_list.append(Msmt('sweater', 'shoulders_raglan', 0))
			else:
				m_list.append(Msmt('sweater', 'sleeve', str2int(strings[4])))
				m_list.append(Msmt('sweater', 'shoulders', str2int(strings[6])))
			# TypeError raised by Measurement class if passed non int value
			# as the measurement value
		except TypeError as e:
			raise UnrecognizedMeasurement((
				'Instantiation of Measurement class ({}) by parsing html raised a KeyError, '
				'indicating the parser identified a region that it expected would be a '
				'measurement value.').format(e), html_string=str(measurements_table_soup))
		except IndexError:
			raise UnrecognizedTemplateHTML((
				'parse_strategy={} expected a differing number of measurements than '
				'what was provided by the template.').format(parse_strategy),
				html_string=str(measurements_table_soup))
	else:
		raise UnsupportedParsingStrategy(
			'Parsing strategy <{}> is not supported for this category'.format(parse_strategy))
	m = MeasurementsCollection(
		parse_strategy=parse_strategy,
		parse_html=str(measurements_table_soup),
		measurements_list=m_list)

	return m
def get_dress_shirt_measurements(measurements_table_soup, parse_strategy='default'):
	"""Parses a dress shirt listing from seller balearic1 and returns a
	MeasurementsCollection instance.

	This parsing function cannot provide qualitative diffrentiation between short and
	long sleeve shirts.

	Parameters
	----------
	measurements_table_soup : BeautifulSoup instance
	parse_strategy='default' : str

	Returns
	-------
	m : MeasurementsCollection instance
	"""

	logger.debug('Attempting to parse as a dress_shirt')

	if type(measurements_table_soup) is not BeautifulSoup:
		raise ValueError('Must be given a BeautifulSoup object')

	m_list = []

	if parse_strategy == 'default':
		logger.debug('Using parse_strategy={}'.format(parse_strategy))
		strings = list(measurements_table_soup.stripped_strings)
		try:
			m_list.append(Msmt('shirt', 'chest_flat', str2int(strings[2])))
			m_list.append(Msmt('shirt', 'shoulders', str2int(strings[6])))
			sleeve_length = str2int(strings[4])
			if sleeve_length >= 18000:
				m_list.append(Msmt('shirt', 'sleeve_long', sleeve_length))
			elif sleeve_length <= 13000:
				m_list.append(Msmt('shirt', 'sleeve_short', sleeve_length))
			else:
				raise UnrecognizedMeasurement(
					'Expected sleeve length to be <= 13000 or >= 18000. \
					Received: <{}>'.format(sleeve_length),
					html_string=str(measurements_table_soup))
			# TypeError raised by Measurement class if passed non int value
			# as the measurement value
		except TypeError as e:
			raise UnrecognizedMeasurement((
				'Instantiation of Measurement class ({}) by parsing html raised a KeyError, '
				'indicating the parser identified a region that it expected would be a '
				'measurement value.').format(e), html_string=str(measurements_table_soup))
		except IndexError:
			raise UnrecognizedTemplateHTML((
				'parse_strategy={} expected a differing number of measurements than '
				'what was provided by the template.').format(parse_strategy),
				html_string=str(measurements_table_soup))
	else:
		raise UnsupportedParsingStrategy(
			'Parsing strategy <{}> is not supported for this category'.format(parse_strategy))
	m = MeasurementsCollection(
		parse_strategy=parse_strategy,
		parse_html=str(measurements_table_soup),
		measurements_list=m_list)

	return m
Beispiel #7
0
def get_sweater_measurements(html_description, parse_strategy='default'):
    """Parses a sweater listing from seller balearic1 and returns a
	MeasurementsCollection instance.

	parse_strategy='default' attempts to detect raglan shoulders and sleeves
	measured from underarm and act accordingly.
	accordingly.

	Parameters
	----------
	html_description : str
	parse_strategy : str
		Defaults to 'default'

	Returns
	-------
	m : MeasurementsCollection instance
	"""

    soup = BeautifulSoup(html_description, 'html.parser')

    try:
        assert soup.find(string='Approximate Measurements') != None
    except AssertionError:
        raise UnrecognizedTemplateHTML(
            'Unable to find "Approximate Measurements" string in HTML description',
            html_string=str(soup))
    else:
        data = (
            soup.find(string='Approximate Measurements')  # string itself
            .parent  # enclosing <h3>
            .parent  # enclosing <td>
            .parent  # enclosing <tr>
            .parent  # enclosing <tbody>
            .parent  # enclosing <table>
        )

    m_list = []

    if parse_strategy == 'default':
        sweater_uses_raglan = data.find(
            string=re.compile('raglan', flags=re.IGNORECASE)) is not None
        sweater_uses_underarm = data.find(
            string=re.compile('underarm', flags=re.IGNORECASE)) is not None

        if sweater_uses_raglan != sweater_uses_underarm:
            raise UnrecognizedTemplateHTML(
                'Expected template text search for "raglan" and "underarm" to BOTH == True\
				or BOTH == False. Found raglan={} and sweater_uses_underarm={}'.format(
                    sweater_uses_raglan, sweater_uses_underarm),
                html_string=str(data))

        strings = list(data.stripped_strings)
        try:
            m_list.append(Msmt('sweater', 'chest_flat', str2int(strings[2])))
            m_list.append(Msmt('sweater', 'length', str2int(strings[8])))

            # Handle cases with raglan sleeves or not
            if sweater_uses_raglan and sweater_uses_underarm:
                m_list.append(
                    Msmt('sweater', 'sleeve_from_armpit', str2int(strings[4])))
                m_list.append(Msmt('sweater', 'shoulders_raglan', 0))
            else:
                m_list.append(Msmt('sweater', 'sleeve', str2int(strings[4])))
                m_list.append(Msmt('sweater', 'shoulders',
                                   str2int(strings[6])))
            # TypeError raised by Measurement class if passed non int value
            # as the measurement value
        except TypeError as e:
            raise UnrecognizedMeasurement(
                'Instantiation of Measurement class ({}) by parsing html raised a KeyError, \
				indicating the parser identified a region that it expected would be a \
				measurement value.'.format(e),
                html_string=str(data))
        except IndexError:
            raise UnrecognizedTemplateHTML(
                'Default parsing strategy expected a differing number of measurements than \
				what was provided by the template.',
                html_string=str(data))
    else:
        raise UnsupportedParsingStrategy(
            'Parsing strategy <{}> is not supported for this category'.format(
                parse_strategy))
    m = MeasurementsCollection(parse_strategy=parse_strategy,
                               parse_html=str(data),
                               measurements_list=m_list)

    return m
Beispiel #8
0
def get_coat_and_jacket_measurements(html_description,
                                     parse_strategy='default'):
    """Parses a coat/jacket listing from seller balearic1 and returns a
	MeasurementsCollection instance.

	Parameters
	----------
	html_description : str
	parse_strategy : str
		Defaults to 'default'

	Returns
	-------
	m : MeasurementsCollection instance
	"""

    logger.debug('Beginning coats&jackets parser')

    soup = BeautifulSoup(html_description, 'html.parser')

    try:
        assert soup.find(string='Approximate Measurements') != None
    except AssertionError:
        raise UnrecognizedTemplateHTML(
            'Unable to find "Approximate Measurements" string in HTML description',
            html_string=str(soup))
    else:
        data = (
            soup.find(string='Approximate Measurements')  # string itself
            .parent  # enclosing <h3>
            .parent  # enclosing <td>
            .parent  # enclosing <tr>
            .parent  # enclosing <tbody>
            .parent  # enclosing <table>
        )

    m_list = []

    logger.debug('Using <%s> parsing strategy' % parse_strategy)

    if parse_strategy == 'default':
        strings = list(data.stripped_strings)
        try:
            m_list.append(Msmt('jacket', 'chest_flat', str2int(strings[2])))
            m_list.append(Msmt('jacket', 'sleeve', str2int(strings[4])))
            m_list.append(Msmt('jacket', 'shoulders', str2int(strings[6])))
            m_list.append(Msmt('jacket', 'length', str2int(strings[8])))
            # TypeError raised by Measurement class if passed non int value
            # as the measurement value
        except TypeError as e:
            raise UnrecognizedMeasurement(
                'Instantiation of Measurement class ({}) by parsing html raised a KeyError, \
				indicating the parser identified a region that it expected would be a \
				measurement value.'.format(e),
                html_string=str(data))
        except IndexError:
            raise UnrecognizedTemplateHTML(
                'Default parsing strategy expected a differing number of measurements than \
				what was provided by the template.',
                html_string=str(data))
    elif parse_strategy == 'new_v1':

        search_for = [
            PP(attribute='sleeve', pattern=re.compile('sleeve',
                                                      re.IGNORECASE)),
            PP(attribute='chest_flat',
               pattern=re.compile('pit to pit', re.IGNORECASE)),
            PP(attribute='shoulders',
               pattern=re.compile('shoulder seams', re.IGNORECASE)),
            PP(attribute='length', pattern=re.compile('length',
                                                      re.IGNORECASE)),
            PP(attribute='waist_flat',
               pattern=re.compile('waist', re.IGNORECASE),
               required=False)
        ]

        for pp in search_for:
            pp.category = 'jacket'

        for parse_param in search_for:
            logger.debug('Searching template for %s, using pattern <%r>' %
                         (parse_param.attribute, parse_param.pattern))

            # Find search phrase in soup
            navigable_str = data.find(string=parse_param.pattern)
            if navigable_str is None:
                if parse_param.required:
                    logger.warn(
                        'get_coat_and_jacket_measurements method did not find a match for pattern: <%r> in the template HTML.'
                        % parse_param.pattern)
                    raise UnrecognizedTemplateHTML(
                        'Parser did not find an expected regex pattern: <{}> in template HTML'
                        .format(repr(parse_param.pattern)),
                        html_string=str(data))
                else:
                    logger.debug('Did not find match')
            else:
                # Find measurement value paired to search phrase
                msmt = navigable_str.find_parent('td').find_next_sibling(
                    'td').string

                if msmt is None:
                    debug.warn(
                        'get_coat_and_jacket_measurements method could not find a sibling measurement for <%r>'
                        % navigable_str)
                    raise UnrecognizedTemplateHTML(
                        'Parser could not find accompanying measurement value for <%r>'
                        .format(navigable_str),
                        html_string=str(data))
                else:
                    # Convert it from text decimal to integer and add to the list
                    m = Msmt(parse_param.category, parse_param.attribute,
                             str2int(msmt))
                    logger.debug('Parsed out and built Measurement: <%r>' % m)
                    m_list.append(m)
        """should_have = [
			('sleeve', 'sleeve'),
			('pit to pit', 'chest_flat'),
			('shoulder', 'shoulders'),
			('length', 'length')]

		could_have = [
			('waist', 'waist_flat')]

		for search_phrase, msmt_type in should_have:
			logger.debug('Searching template for <%r>' % search_phrase)

			# Find search phrase in soup
			navigable_str = data.find(string=re.compile(search_phrase, re.IGNORECASE))

			if navigable_str is None:
				logger.warn(
					'get_coat_and_jacket_measurements method did not find an expected string: <%r> in the template HTML.' % navigable_str)
				raise UnrecognizedTemplateHTML(
					'Parser did not find an expected string: <{}> in template HTML'
					.format(navigable_str),
					html_string=str(data))
			else:
				# Find measurement value paired to search phrase
				msmt = navigable_str.find_parent('td').find_next_sibling('td').string
				if msmt is None:
					logger.warn(
						'get_coat_and_jacket_measurements method did not find paired meaasurement for: <%r> in the template HTML.' % navigable_str)
					raise UnrecognizedMeasurement(
						'Search for a measurement value paired to the string <{}> failed.'.format(search_phrase))

				# Convert it from text decimal to integer and add to the list
				m = Msmt('jacket', msmt_type, str2int(msmt))
				logger.debug('Parsed out and built Measurement: %r' % m)
				m_list.append(m)

		# Build 'could haves' (Spoo doesn't list waist measurements for casual coats and jackets)

		for search_phrase, msmt_type in could_have:
			logger.debug('Searching template for <%r>' % search_phrase)

			# Find search phrase in soup
			navigable_str = data.find(string=re.compile(search_phrase, re.IGNORECASE))

			if navigable_str is None:
				logger.debug(
					'get_coat_and_jacket_measurements method did not find string: <%r> in the template HTML.' % navigable_str)
			else:
				# Find measurement value paired to search phrase
				msmt = navigable_str.find_parent('td').find_next_sibling('td').string
				if msmt is None:
					logger.warn(
						'get_coat_and_jacket_measurements method did not find paired meaasurement for: <%r> in the template HTML.' % navigable_str)
					raise UnrecognizedMeasurement(
						'Search for a measurement value paired to the string <{}> failed.'.format(search_phrase))

				# Convert it from text decimal to integer and add to the list
				m = Msmt('jacket', msmt_type, str2int(msmt))
				logger.debug('Parsed out and built Measurement: %r' % m)
				m_list.append(m)"""

    else:
        raise UnsupportedParsingStrategy(
            'Parsing strategy <{}> is not supported for this category'.format(
                parse_strategy))
    m = MeasurementsCollection(parse_strategy=parse_strategy,
                               parse_html=str(data),
                               measurements_list=m_list)

    return m
Beispiel #9
0
def get_dress_shirt_measurement(html_description, parse_strategy='default'):
    """Parses a dress shirt listing from seller balearic1 and returns a
	MeasurementsCollection instance.

	This parsing function cannot provide qualitative diffrentiation between short and
	long sleeve shirts.

	Parameters
	----------
	html_description : str
	parse_strategy : str
		Defaults to 'default'

	Returns
	-------
	m : MeasurementsCollection instance
	"""

    soup = BeautifulSoup(html_description, 'html.parser')

    try:
        assert soup.find(string='Approximate Measurements') != None
    except AssertionError:
        raise UnrecognizedTemplateHTML(
            'Unable to find "Approximate Measurements" string in HTML description',
            html_string=str(soup))
    else:
        data = (
            soup.find(string='Approximate Measurements')  # string itself
            .parent  # enclosing <h3>
            .parent  # enclosing <td>
            .parent  # enclosing <tr>
            .parent  # enclosing <tbody>
            .parent  # enclosing <table>
        )

    m_list = []

    if parse_strategy == 'default':
        strings = list(data.stripped_strings)
        try:
            m_list.append(Msmt('shirt', 'chest_flat', str2int(strings[2])))
            m_list.append(Msmt('shirt', 'shoulders', str2int(strings[6])))
            sleeve_length = str2int(strings[4])
            if sleeve_length >= 18000:
                m_list.append(Msmt('shirt', 'sleeve_long', sleeve_length))
            elif sleeve_length <= 13000:
                m_list.append(Msmt('shirt', 'sleeve_short', sleeve_length))
            else:
                raise UnrecognizedMeasurement(
                    'Expected sleeve length to be <= 13000 or >= 18000. \
					Received: <{}>'.format(sleeve_length),
                    html_string=str(data))
            # TypeError raised by Measurement class if passed non int value
            # as the measurement value
        except TypeError as e:
            raise UnrecognizedMeasurement(
                'Instantiation of Measurement class ({}) by parsing html raised a KeyError, \
				indicating the parser identified a region that it expected would be a \
				measurement value.'.format(e),
                html_string=str(data))
        except IndexError:
            raise UnrecognizedTemplateHTML(
                'Default parsing strategy expected a differing number of measurements than \
				what was provided by the template.',
                html_string=str(data))
    else:
        raise UnsupportedParsingStrategy(
            'Parsing strategy <{}> is not supported for this category'.format(
                parse_strategy))
    m = MeasurementsCollection(parse_strategy=parse_strategy,
                               parse_html=str(data),
                               measurements_list=m_list)

    return m