def __init__(self,
url=DEFAULT_BASE_URL,
credentials=DEFAULT_CREDENTIALS,
schema=DEFAULT_SCHEMA,
verbose=False):
# get input(s)
self.url = url
self.credentials = credentials
self.schema = schema
self.verbose = verbose
# private variable(s)
self.__response = None
self.__soup = None
self.__username, self.__password = self.__credentials.split(f':')
self.__after = []
self.__aka = []
self.__before = []
self.__dates = []
self.__events = []
self.__names = []
self.__columns = 0
self.__headers = []
self.__rows = 0
self.__authorization = {
'username': self.__username,
'password': self.__password
}
self.__user_agent = {
'user-agent': TNS_USER_AGENT.replace('<username>', self.__username)
}
# verbose
self.__log = UtilsLogger(
'LigoQ3cScrapeUserAgent').logger if self.__verbose else None
if self.__verbose:
self.__log.info(f"url='{self.__url}'")
self.__log.info(f"credentials='{self.__credentials}'")
self.__log.info(f"schema={self.__schema}")
self.__log.info(f"verbose={self.__verbose}")
self.__log.info(f"log={self.__log}")
self.__log.info(f"authorization={self.__authorization}")
self.__log.info(f"user_agent={self.__user_agent}")
# login
try:
self.__session = requests.Session()
self.__session.post(f'{self.__url}/user', data=self.__user_agent)
except Exception as e:
self.__session = None
self.__log.debug(f"self.__session={self.__session}, error={e}")
def __init__(self,
url=DEFAULT_LOGIN_URL,
credentials=DEFAULT_CREDENTIALS,
number=DEFAULT_NUMBER,
unit=DEFAULT_UNIT,
verbose=False):
# get input(s)
self.url = url
self.credentials = credentials
self.number = number
self.unit = unit
self.verbose = verbose
# private variable(s)
self.__ans = None
self.__log = None
self.__response = None
self.__soup = None
self.__params = None
self.__pages = -1
self.__session = None
self.__total = -1
self.__user_agent = None
self.__authorization = {
'username': self.__username,
'password': self.__password
}
self.__user_agent = {
'user-agent': TNS_USER_AGENT.replace('<username>', self.__username)
}
# verbose
self.__log = UtilsLogger(
'TnsQ3cScrapeUserAgent').logger if self.__verbose else None
if self.__verbose:
self.__log.info(f"url='{self.__url}'")
self.__log.info(f"credentials='{self.__credentials}'")
self.__log.info(f"number={self.__number}")
self.__log.info(f"unit='{self.__unit}'")
self.__log.info(f"verbose={self.__verbose}")
self.__log.info(f"log={self.__log}")
self.__log.info(f"authorization={self.__authorization}")
self.__log.info(f"user_agent={self.__user_agent}")
# login
try:
self.__session = requests.Session()
self.__session.post(self.__url, data=self.__user_agent)
except Exception as e:
self.__session = None
self.__log.debug(f"self.__session={self.__session}, error={e}")
class LigoQ3cTableParser(object):
# +
# method: __init__()
# -
def __init__(self,
url=DEFAULT_BASE_URL,
credentials=DEFAULT_CREDENTIALS,
schema=DEFAULT_SCHEMA,
verbose=False):
# get input(s)
self.url = url
self.credentials = credentials
self.schema = schema
self.verbose = verbose
# private variable(s)
self.__response = None
self.__soup = None
self.__username, self.__password = self.__credentials.split(f':')
self.__after = []
self.__aka = []
self.__before = []
self.__dates = []
self.__events = []
self.__names = []
self.__columns = 0
self.__headers = []
self.__rows = 0
self.__authorization = {
'username': self.__username,
'password': self.__password
}
self.__user_agent = {
'user-agent': TNS_USER_AGENT.replace('<username>', self.__username)
}
# verbose
self.__log = UtilsLogger(
'LigoQ3cScrapeUserAgent').logger if self.__verbose else None
if self.__verbose:
self.__log.info(f"url='{self.__url}'")
self.__log.info(f"credentials='{self.__credentials}'")
self.__log.info(f"schema={self.__schema}")
self.__log.info(f"verbose={self.__verbose}")
self.__log.info(f"log={self.__log}")
self.__log.info(f"authorization={self.__authorization}")
self.__log.info(f"user_agent={self.__user_agent}")
# login
try:
self.__session = requests.Session()
self.__session.post(f'{self.__url}/user', data=self.__user_agent)
except Exception as e:
self.__session = None
self.__log.debug(f"self.__session={self.__session}, error={e}")
# +
# decorator(s)
# -
@property
def url(self):
return self.__url
@url.setter
def url(self, url):
self.__url = url if (isinstance(url, str) and url.strip() != f'' and
url.lower().startswith(f'http')) else DEFAULT_URL
@property
def credentials(self):
return self.__credentials
@credentials.setter
def credentials(self, credentials):
self.__credentials = credentials if (
isinstance(credentials, str) and credentials.strip() != f''
and f':' in credentials) else DEFAULT_CREDENTIALS
self.__username, self.__password = self.__credentials.split(f':')
@property
def log(self):
return self.__log
@log.setter
def log(self, log):
self.__log = UtilsLogger(
'LigoQ3cScrapeUserAgent').logger if self.__verbose else None
@property
def schema(self):
return self.__schema
@schema.setter
def schema(self, schema):
self.__schema = schema.lower(
) if schema in TNS_LIGO_SUPPORTED_SCHEMAS else DEFAULT_SCHEMA
@property
def verbose(self):
return self.__verbose
@verbose.setter
def verbose(self, verbose):
self.__verbose = verbose if isinstance(verbose, bool) else False
@property
def authorization(self):
return self.__authorization
@property
def user_agent(self):
return self.__user_agent
# +
# method: dump()
# -
@staticmethod
def dump(_item=None, _delimiter='\n'):
if _item is None:
_res = f''
elif isinstance(_item, tuple) and _item is not ():
_res = f''.join(f'{_v}{_delimiter}' for _v in _item)[:-1]
elif isinstance(_item, list) and _item is not []:
_res = f''.join(f'{_v}{_delimiter}' for _v in _item)[:-1]
elif isinstance(_item, set) and _item is not {}:
_res = f''.join(f'{_v}{_delimiter}' for _v in _item)[:-1]
elif isinstance(_item, dict) and _item is not {}:
_res = f''.join(f'{_k}={_v}{_delimiter}'
for _k, _v in _item.items())[:-1]
else:
_res = f'{str(_item)}'
return _res
# +
# method: get_after()
# -
def get_after(self, _table=None):
""" gets links labelled as after the event """
# check input(s)
self.__after = []
if _table is None or not hasattr(_table, f'find_all'):
return
# find <td class="cell-downloads"></td> elements
for _td in _table.find_all('td', attrs={'class': 'cell-downloads'}):
# find <a href="/ligo/event/*"></a> elements
for _a in _td.find_all('a', href=True):
# check names are in correct format
if _a['href'].strip().lower().startswith(f'http') \
and _a['href'].strip().lower().endswith(self.__schema):
# check for search pattern
if f'after' in _a['href'].strip().lower(
) and f"{_a['href'].strip()}" not in self.__after:
self.__after.append(f"{_a['href'].strip()}")
# +
# method: get_aka()
# -
def get_aka(self, _table=None):
""" get the also-known-as name of the event """
# check input(s)
self.__aka = []
if _table is None or not hasattr(_table, f'find_all'):
return
# find <td class="cell-name"></td> elements
for _td in _table.find_all('td', attrs={'class': 'cell-name'}):
# find <a href="/ligo/event/*"></a> elements
for _a in _td.find_all('a', href=True):
# check names are in correct format
if _a['href'].lower().startswith(f'/ligo/event'):
# check for search pattern
m = TNS_LIGO_SUPPORTED_EVENTS.search(_a['href'])
if m and f'{m.group().strip()}' not in self.__aka:
self.__aka.append(f'{m.group()}')
# +
# method: get_attributes()
# -
def get_attributes(self, _table=None):
""" get table attributes """
# check input(s)
self.__columns, self.__headers, self.__rows = 0, [], 0
if _table is None or not hasattr(_table, f'find_all'):
return
# get headers
for _th in _table.find_all('th'):
if f'{_th.text.strip()}' not in self.__headers:
self.__headers.append(f'{_th.text.strip()}')
# get number of columns
self.__columns = len(self.__headers)
# get number of rows
for row in _table.find_all('tr'):
if len(row.find_all('td')) > 0:
self.__rows += 1
if self.__verbose:
self.__log.debug(f"self.__columns={self.__columns}")
self.__log.debug(f"self.__headers={self.__headers}")
self.__log.debug(f"self.__rows={self.__rows}")
# +
# method: get_before()
# -
def get_before(self, _table=None):
""" gets links labelled as before the event """
# check input(s)
self.__before = []
if _table is None or not hasattr(_table, f'find_all'):
return
# find <td class="cell-downloads"></td> elements
for _td in _table.find_all('td', attrs={'class': 'cell-downloads'}):
# find <a href="/ligo/event/*"></a> elements
for _a in _td.find_all('a', href=True):
# check names are in correct format
if _a['href'].strip().lower().startswith(f'http') \
and _a['href'].strip().lower().endswith(self.__schema):
# check for search pattern
if f'before' in _a['href'].strip().lower(
) and f"{_a['href'].strip()}" not in self.__before:
self.__before.append(f"{_a['href'].strip()}")
# +
# method: get_dates()
# -
def get_dates(self, _table=None):
""" get dates of events """
# check input(s)
self.__dates = []
if _table is None or not hasattr(_table, f'find_all'):
return
# find <td class="cell-date"></td> elements
for _td in _table.find_all('td', attrs={'class': 'cell-date'}):
if f'{_td.text.strip()}' not in self.__dates:
self.__dates.append(f'{_td.text.strip()}')
# +
# method: get_events()
# -
def get_events(self, _table=None):
""" get all data associated with events """
# check input(s)
if _table is None or not hasattr(_table, f'find_all'):
return {}
# get data
self.get_attributes(_table)
self.get_after(_table)
self.get_aka(_table)
self.get_before(_table)
self.get_dates(_table)
self.get_names(_table)
# message(s)
if self.__verbose:
self.__log.debug(
f"self.__after={self.dump(self.__after, ' ')}, len={len(self.__after)}"
)
self.__log.debug(
f"self.__aka={self.dump(self.__aka, ' ')}, len={len(self.__aka)}"
)
self.__log.debug(
f"self.__before={self.dump(self.__before, ' ')}, len={len(self.__before)}"
)
self.__log.debug(
f"self.__dates={self.dump(self.__dates, ' ')}, len={len(self.__dates)}"
)
self.__log.debug(
f"self.__names={self.dump(self.__names, ' ')}, len={len(self.__names)}"
)
# return - this is horrible, it really needs splitting up somehow
_ans = {}
for _i in range(self.__rows):
if self.__verbose:
self.__log.debug(f"scraping row {_i}")
# get before data from json
if self.__schema == 'json' and list_has_index(self.__before, _i):
_before = self.scrape_json(self.__before[_i])
if _before is not None:
for _bk, _bv in _before.items():
_name = f"{self.__names[_i]}-{_bk.strip()}"
_suffix = f'{get_unique_hash()}'[:6]
if f'{_name}' in _ans:
_name = f'{_name}-{_suffix}'
if self.__verbose:
self.__log.debug(
f"Creating new dictionary element, _ans['{_name}']"
)
_ans[f'{_name}'] = {
'name':
f'{_name}',
'name_prefix':
_bv['name_prefix'] if 'name_prefix' in _bv else '',
'name_suffix':
_suffix if f'{_suffix}' in _name else '',
'ra':
float(_bv['ra']) if 'ra' in _bv else math.nan,
'dec':
float(_bv['dec']) if 'dec' in _bv else math.nan,
'transient_type':
_bv['type'] if 'type' in _bv else '',
'discovery_date':
_bv['discoverydate']
if 'discoverydate' in _bv else '',
'discovery_mag':
float(_bv['discoverymag'])
if 'discoverymag' in _bv else math.nan,
'filter_name':
_bv['filter'] if 'filter' in _bv else '',
'source_group':
_bv['source_group']
if 'source_group' in _bv else '',
'probability':
float(_bv['probability'])
if 'probability' in _bv else math.nan,
'sigma':
float(_bv['sigma'])
if 'sigma' in _bv else math.nan,
'gw_aka':
self.__aka[_i],
'gw_event':
self.__names[_i],
'gw_date':
self.__dates[_i],
'before':
True
}
# get before data from tsv
elif self.__schema == 'tsv' and list_has_index(self.__before, _i):
_before = self.scrape_tsv(self.__before[_i])
if _before is not None:
_before = _before.split('\n')
_hdr = _before[0].split('\t')
for _e in _before[1:]:
_before_entry = dict(zip(_hdr, _e.split('\t')))
if len(_hdr) != len(_before_entry):
continue
_name = f"{self.__names[_i]}-{_before_entry['name'].strip()}"
_suffix = f'{get_unique_hash()}'[:6]
if f'{_name}' in _ans:
_name = f'{_name}-{_suffix}'
if self.__verbose:
self.__log.debug(
f"Creating new dictionary element, _ans['{_name}']"
)
_ans[f'{_name}'] = {
'name':
f'{_name}',
'name_prefix':
_before_entry['name_prefix']
if 'name_prefix' in _before_entry else '',
'name_suffix':
_suffix if f'{_suffix}' in _name else '',
'ra':
float(_before_entry['ra'])
if 'ra' in _before_entry else math.nan,
'dec':
float(_before_entry['dec'])
if 'dec' in _before_entry else math.nan,
'transient_type':
_before_entry['type']
if 'type' in _before_entry else '',
'discovery_date':
_before_entry['discoverydate']
if 'discoverydate' in _before_entry else '',
'discovery_mag':
float(_before_entry['discoverymag'])
if 'discoverymag' in _before_entry else math.nan,
'filter_name':
_before_entry['filter']
if 'filter' in _before_entry else '',
'source_group':
_before_entry['source_group']
if 'source_group' in _before_entry else '',
'probability':
float(_before_entry['probability'])
if 'probability' in _before_entry else math.nan,
'sigma':
float(_before_entry['sigma'])
if 'sigma' in _before_entry else math.nan,
'gw_aka':
self.__aka[_i],
'gw_event':
self.__names[_i],
'gw_date':
self.__dates[_i],
'before':
True
}
# get after data from json
if self.__schema == 'json' and list_has_index(self.__after, _i):
_after = self.scrape_json(self.__after[_i])
if _after is not None:
for _ak, _av in _after.items():
_name = f"{self.__names[_i]}-{_ak.strip()}"
_suffix = f'{get_unique_hash()[:6]}'
if f'{_name}' in _ans:
_name = f'{_name}-{_suffix}'
if self.__verbose:
self.__log.debug(
f"Creating new dictionary element, _ans['{_name}']"
)
_ans[f'{_name}'] = {
'name':
f'{_name}',
'name_prefix':
_av['name_prefix'] if 'name_prefix' in _av else '',
'name_suffix':
_suffix if f'{_suffix}' in _name else '',
'ra':
float(_av['ra']) if 'ra' in _av else math.nan,
'dec':
float(_av['dec']) if 'dec' in _av else math.nan,
'transient_type':
_av['type'] if 'type' in _av else '',
'discovery_date':
_av['discoverydate']
if 'discoverydate' in _av else '',
'discovery_mag':
float(_av['discoverymag'])
if 'discoverymag' in _av else math.nan,
'filter_name':
_av['filter'] if 'filter' in _av else '',
'source_group':
_av['source_group']
if 'source_group' in _av else '',
'probability':
float(_av['probability'])
if 'probability' in _av else math.nan,
'sigma':
float(_av['sigma'])
if 'sigma' in _av else math.nan,
'gw_aka':
self.__aka[_i],
'gw_event':
self.__names[_i],
'gw_date':
self.__dates[_i],
'before':
False
}
# get after data from tsv
elif self.__schema == 'tsv' and list_has_index(self.__after, _i):
_after = self.scrape_tsv(self.__after[_i])
if _after is not None:
_after = _after.split('\n')
_hdr = _after[0].split('\t')
for _e in _after[1:]:
_after_entry = dict(zip(_hdr, _e.split('\t')))
if len(_hdr) != len(_after_entry):
continue
_name = f"{self.__names[_i]}-{_after_entry['name'].strip()}"
_suffix = f'{get_unique_hash()[:6]}'
if f'{_name}' in _ans:
_name = f'{_name}-{_suffix}'
if self.__verbose:
self.__log.debug(
f"Creating new dictionary element, _ans['{_name}']"
)
_ans[f'{_name}'] = {
'name':
f'{_name}',
'name_prefix':
_after_entry['name_prefix']
if 'name_prefix' in _after_entry else '',
'name_suffix':
_suffix if f'{_suffix}' in _name else '',
'ra':
float(_after_entry['ra'])
if 'ra' in _after_entry else math.nan,
'dec':
float(_after_entry['dec'])
if 'dec' in _after_entry else math.nan,
'transient_type':
_after_entry['type']
if 'type' in _after_entry else '',
'discovery_date':
_after_entry['discoverydate']
if 'discoverydate' in _after_entry else '',
'discovery_mag':
float(_after_entry['discoverymag'])
if 'discoverymag' in _after_entry else math.nan,
'filter_name':
_after_entry['filter']
if 'filter' in _after_entry else '',
'source_group':
_after_entry['source_group']
if 'source_group' in _after_entry else '',
'probability':
float(_after_entry['probability'])
if 'probability' in _after_entry else math.nan,
'sigma':
float(_after_entry['sigma'])
if 'sigma' in _after_entry else math.nan,
'gw_aka':
self.__aka[_i],
'gw_event':
self.__names[_i],
'gw_date':
self.__dates[_i],
'before':
False
}
# return
return _ans
# +
# method: get_names()
# -
def get_names(self, _table=None):
""" get names of events """
# check input(s)
self.__names = []
if _table is None or not hasattr(_table, f'find_all'):
return
# find <td class="cell-name"></td> elements
for _td in _table.find_all('td', attrs={'class': 'cell-name'}):
# find <a href="/ligo/event/*"></a> elements
for _a in _td.find_all('a', href=True):
# check names are in correct format
if _a['href'].lower().startswith(f'/ligo/event'):
self.__names.append(f'{_a.text.strip()}')
# +
# method: get_request()
# -
def get_request(self):
""" get data from web-site """
# noinspection PyBroadException
try:
if self.__verbose:
self.__log.debug(
f"Calling requests.get('{self.__url}', auth='{self.__username, self.__password}')"
)
_requests = requests.get(f'{self.__url}/ligo/events',
headers=self.__user_agent,
auth=(self.__username, self.__password))
if self.__verbose:
self.__log.debug(
f"Called requests.get('{self.__url}', "
f"auth='{self.__username, self.__password}'), _requests={_requests}"
)
if _requests.status_code == 200:
return _requests
else:
if self.__verbose:
self.__log.error(
f"Bad status code ({_requests.status_code}) calling requests.get('{self.__url}', "
f"auth='{self.__username, self.__password}')")
return None
except Exception as e:
if self.__verbose:
self.__log.error(
f"Failed calling requests.get('{self.__url}', "
f"auth='{self.__username, self.__password}'), error={e}")
return None
# +
# method: scrape_json()
# -
def scrape_json(self, _url=''):
""" get json data from web-site """
# return data
if _url.strip().lower().startswith(
f'http') and _url.strip().lower().endswith('json'):
self.__url = _url
self.__response = self.get_request()
if self.__response is not None:
return self.__response.json()
else:
return None
# +
# method: scrape_tsv()
# -
def scrape_tsv(self, _url=''):
""" get tsv data from web-site """
# return data
if _url.strip().lower().startswith(
f'http') and _url.strip().lower().endswith('tsv'):
self.__url = _url
self.__response = self.get_request()
if self.__response is not None:
return self.__response.content.decode()
else:
return None
# +
# method: scrape_ligo_q3c_events()
# -
def scrape_ligo_q3c_events(self):
""" scrape web-site for ligo_q3c events """
# get data
self.__response = self.get_request()
if self.__verbose:
self.__log.debug(f'self.__response={self.__response}')
# check response
if self.__response is None:
return [], 0
# set up encoding
_http_encoding = self.__response.encoding if 'charset' in self.__response.headers.get(
'content-type', '').lower() else None
_html_encoding = EncodingDetector.find_declared_encoding(
self.__response.content, is_html=True)
# return data
try:
self.__soup = BeautifulSoup(self.__response.text,
features='html5lib',
from_encoding=(_html_encoding
or _http_encoding))
except Exception as e:
if self.__verbose:
self.__log.error(
f'Failed to get soup from self.__response, error={e}')
return [], 0
if self.__verbose:
self.__log.info(
self.__soup.find_all('table',
attrs={'class': 'ligo-alerts-table'}))
try:
_ret = [
self.get_events(_t) for _t in self.__soup.find_all(
'table', attrs={'class': 'ligo-alerts-table'})
]
return _ret, len(_ret)
except Exception as e:
if self.__verbose:
self.__log.error(
f'Failed to get events from self.__response, error={e}')
return [], 0
def log(self, log):
self.__log = UtilsLogger(
'LigoQ3cScrapeUserAgent').logger if self.__verbose else None
from src.models.ligo_q3c import LigoQ3cRecord
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
# noinspection PyUnresolvedReferences
from utils import UtilsLogger
# +
# suppress all warnings!
# -
warnings.filterwarnings('ignore')
# +
# logging
# -
_log = UtilsLogger('LigoQ3c').logger
# +
# default(s)
# -
DEFAULT_BASE_URL = f'https://www.wis-tns.org'
DEFAULT_LOGIN_URL = f'{DEFAULT_BASE_URL}/user'
DEFAULT_SEARCH_URL = f'{DEFAULT_BASE_URL}/ligo/events'
DEFAULT_CREDENTIALS = f':'
DEFAULT_SCHEMA = f'json'
# +
# constant(s)
# -
SASSY_DB_HOST = os.getenv('SASSY_DB_HOST', None)
SASSY_DB_NAME = os.getenv('SASSY_DB_NAME', None)
class TnsQ3cTableParser(object):
# +
# method: __init__()
# -
def __init__(self,
url=DEFAULT_LOGIN_URL,
credentials=DEFAULT_CREDENTIALS,
number=DEFAULT_NUMBER,
unit=DEFAULT_UNIT,
verbose=False):
# get input(s)
self.url = url
self.credentials = credentials
self.number = number
self.unit = unit
self.verbose = verbose
# private variable(s)
self.__ans = None
self.__log = None
self.__response = None
self.__soup = None
self.__params = None
self.__pages = -1
self.__session = None
self.__total = -1
self.__user_agent = None
self.__authorization = {
'username': self.__username,
'password': self.__password
}
self.__user_agent = {
'user-agent': TNS_USER_AGENT.replace('<username>', self.__username)
}
# verbose
self.__log = UtilsLogger(
'TnsQ3cScrapeUserAgent').logger if self.__verbose else None
if self.__verbose:
self.__log.info(f"url='{self.__url}'")
self.__log.info(f"credentials='{self.__credentials}'")
self.__log.info(f"number={self.__number}")
self.__log.info(f"unit='{self.__unit}'")
self.__log.info(f"verbose={self.__verbose}")
self.__log.info(f"log={self.__log}")
self.__log.info(f"authorization={self.__authorization}")
self.__log.info(f"user_agent={self.__user_agent}")
# login
try:
self.__session = requests.Session()
self.__session.post(self.__url, data=self.__user_agent)
except Exception as e:
self.__session = None
self.__log.debug(f"self.__session={self.__session}, error={e}")
# +
# decorator(s)
# -
@property
def url(self):
return self.__url
@url.setter
def url(self, url):
self.__url = url if (
isinstance(url, str)
and url.lower().startswith(f'http')) else DEFAULT_LOGIN_URL
@property
def credentials(self):
return self.__credentials
@credentials.setter
def credentials(self, credentials):
self.__credentials = credentials if (isinstance(
credentials, str) and f':' in credentials) else DEFAULT_CREDENTIALS
self.__username, self.__password = self.__credentials.split(f':')
@property
def log(self):
return self.__log
@log.setter
def log(self, log):
self.__log = UtilsLogger(
'TnsQ3cScrapeUserAgent').logger if self.__verbose else None
@property
def number(self):
return self.__number
@number.setter
def number(self, number):
self.__number = number if (isinstance(number, int)
and number > 0) else DEFAULT_NUMBER
@property
def unit(self):
return self.__unit
@unit.setter
def unit(self, unit):
self.__unit = unit if (isinstance(unit, str)
and unit in DEFAULT_UNITS) else DEFAULT_UNIT
@property
def verbose(self):
return self.__verbose
@verbose.setter
def verbose(self, verbose):
self.__verbose = verbose if isinstance(verbose, bool) else False
@property
def athorization(self):
return self.__athorization
@property
def user_agent(self):
return self.__user_agent
# +
# method: dump()
# -
def dump(self, _item=None, _delimiter='\n'):
if _item is None:
_res = f''
elif isinstance(_item, tuple) and _item is not ():
_res = f''.join(f'{_v}{_delimiter}' for _v in _item)[:-1]
elif isinstance(_item, list) and _item is not []:
_res = f''.join(f'{_v}{_delimiter}' for _v in _item)[:-1]
elif isinstance(_item, set) and _item is not {}:
_res = f''.join(f'{_v}{_delimiter}' for _v in _item)[:-1]
elif isinstance(_item, dict) and _item is not {}:
_res = f''.join(f'{_k}={_v}{_delimiter}'
for _k, _v in _item.items())[:-1]
elif isinstance(_item, str) and _item.strip().lower() == 'variables':
_res = f'self.__url = {self.__url}, '
_res += f'self.__credentials = {self.__credentials}, '
_res += f'self.__number = {self.__number}, '
_res += f'self.__unit = {self.__unit}, '
_res += f'self.__verbose = {self.__verbose}, '
_res += f'self.__response = {self.__response}, '
_res += f'self.__params = {self.__params}, '
_res += f'self.__soup = {self.__soup}, '
_res += f'self.__session = {self.__session}, '
_res += f'self.__authorization = {self.__authorization}, '
_res += f'self.__user_agent = {self.__user_agent}, '
_res += f'self.__username = {self.__username}, '
_res += f'self.__password = {self.__password}, '
_res += f'self.__ans = {self.__ans}, '
_res += f'self.__pages = {self.__pages}, '
_res += f'self.__total = {self.__total}, '
else:
_res = f'{str(_item)}'
return _res
# +
# method: get_request()
# -
def get_request(self):
""" get data from web-site """
# noinspection PyBroadException
try:
if self.__session is not None:
_requests = self.__session.get(
url=self.__url,
headers=self.__user_agent,
params=self.__params,
)
else:
_requests = requests.get(
url=self.__url,
headers=self.__user_agent,
params=self.__params,
auth=(self.__username, self.__password),
)
except Exception as e:
if self.__verbose:
self.__log.error(
f"Failed calling self.get_request(), error={e}")
return None
# return data
if _requests.status_code != 200 or _requests.text.strip() == '':
if self.__verbose:
self.__log.error(
f"Bad response (code={_requests.status_code}, text='{_requests.text[1:80]}...')"
)
return None
else:
return _requests
# +
# method: get_records()
# -
def get_records(self):
""" scrape records from soup """
# get the results table and extract rows we want
_table = self.__soup.find_all(
'table', attrs={'class': 'results-table sticky-enabled'})
_repe = [
_e.find_all('tr', attrs={'class': 'row-even public even'})
for _e in _table
][0]
_repo = [
_e.find_all('tr', attrs={'class': 'row-even public odd'})
for _e in _table
][0]
_rope = [
_e.find_all('tr', attrs={'class': 'row-odd public even'})
for _e in _table
][0]
_ropo = [
_e.find_all('tr', attrs={'class': 'row-odd public odd'})
for _e in _table
][0]
if self.__verbose:
self.__log.info(f"len(_repe)={len(_repe)}")
self.__log.info(f"len(_repo)={len(_repo)}")
self.__log.info(f"len(_rope)={len(_rope)}")
self.__log.info(f"len(_ropo)={len(_ropo)}")
_evens = set().union(_repe, _repo)
_odds = set().union(_rope, _ropo)
if self.__verbose:
self.__log.info(f"len(_evens)={len(_evens)}")
self.__log.info(f"len(_odds)={len(_odds)}")
_rows = list(set().union(_evens, _odds))
if self.__verbose:
self.__log.info(f"len(_rows)={len(_rows)}")
# scrape each row which should look like this
for _e in _rows:
# ignore elements that have no find original_all
if not (hasattr(_e, 'find') or hasattr(_e, 'find_all')):
continue
# initialize a dictionary
if self.__verbose:
self.__log.info(f"scraping row {_e}")
_ans_tmp = {}
try:
# <td class="cell-id">6565</td>
_ans_tmp['tns_id'] = _e.find('td', attrs={
'class': 'cell-id'
}).text.strip()
except Exception:
_ans_tmp['tns_id'] = ''
try:
# <td class="cell-name"><a href="/object/2015z">SN 2015Z</a></td>
_ans_tmp['tns_name'] = (_e.find(
'td', attrs={'class':
'cell-name'})).find('a').text.strip()
_link = (_e.find('td',
attrs={'class':
'cell-name'})).find('a',
href=True)['href']
_ans_tmp['tns_link'] = f"{DEFAULT_BASE_URL}{_link}"
except Exception:
_ans_tmp['tns_name'] = ''
_ans_tmp['tns_link'] = ''
try:
# <td class="cell-reps">1<a class="cert-open" href="/object/2019oel/discovery-cert" rel="43659"></a>
# <a class="at-reps-open clearfix" href="/%23" rel="43659"></a></td>
_cert = (_e.find('td',
attrs={'class':
'cell-reps'})).find('a',
href=True)['href']
_ans_tmp['tns_cert'] = f"{DEFAULT_BASE_URL}{_cert}"
except Exception:
_ans_tmp['tns_cert'] = ''
try:
# <td class="cell-class"></td>
_ans_tmp['tns_class'] = _e.find('td',
attrs={
'class': 'cell-class'
}).text.strip()
except Exception:
_ans_tmp['tns_class'] = ''
try:
# <td class="cell-ra">17:18:23.982</td>
_ans_tmp['ra'] = _e.find('td', attrs={
'class': 'cell-ra'
}).text.strip()
except Exception:
_ans_tmp['ra'] = ''
try:
# <td class="cell-decl">-31:04:29.63</td>
_ans_tmp['decl'] = _e.find('td', attrs={
'class': 'cell-decl'
}).text.strip()
except Exception:
_ans_tmp['decl'] = ''
try:
# <td class="cell-ot_name"></td>
_ans_tmp['ot_name'] = _e.find('td',
attrs={
'class': 'cell-ot_name'
}).text.strip()
except Exception:
_ans_tmp['ot_name'] = ''
try:
# <td class="cell-redshift"></td>
_ans_tmp['redshift'] = _e.find('td',
attrs={
'class': 'cell-redshift'
}).text.strip()
except Exception:
_ans_tmp['redshift'] = ''
try:
# <td class="cell-hostname"></td>
_ans_tmp['hostname'] = _e.find('td',
attrs={
'class': 'cell-hostname'
}).text.strip()
except Exception:
_ans_tmp['hostname'] = ''
try:
# <td class="cell-host_redshift"></td>
_ans_tmp['host_redshift'] = _e.find('td',
attrs={
'class':
'cell-host_redshift'
}).text.strip()
except Exception:
_ans_tmp['host_redshift'] = ''
try:
# <td class="cell-source_group_name">ATLAS</td>
_ans_tmp['source_group'] = _e.find('td',
attrs={
'class':
'cell-source_group_name'
}).text.strip()
except Exception:
_ans_tmp['source_group'] = ''
try:
# <td class="cell-classifying_source_group_name"></td>
_ans_tmp['classifying_group'] = _e.find(
'td',
attrs={
'class': 'cell-classifying_source_group_name'
}).text.strip()
except Exception:
_ans_tmp['classifying_group'] = ''
try:
# <td class="cell-groups">ATLAS</td>
_ans_tmp['groups'] = _e.find('td',
attrs={
'class': 'cell-groups'
}).text.strip()
except Exception:
_ans_tmp['groups'] = ''
try:
# <td class="cell-internal_name">ATLAS19svo</td>
_ans_tmp['internal_name'] = _e.find('td',
attrs={
'class':
'cell-internal_name'
}).text.strip()
except Exception:
_ans_tmp['internal_name'] = ''
try:
# <td class="cell-discovering_instrument_name">ATLAS1 - ACAM1</td>
_ans_tmp['instrument_name'] = _e.find(
'td', attrs={
'class': 'cell-discovering_instrument_name'
}).text.strip()
except Exception:
_ans_tmp['instrument_name'] = ''
try:
# <td class="cell-classifing_instrument_name"></td>
_ans_tmp['classifying_instrument'] = _e.find(
'td', attrs={
'class': 'cell-classifing_instrument_name'
}).text.strip()
except Exception:
_ans_tmp['classifying_instrument'] = ''
try:
# <td class="cell-isTNS_AT">Y</td>
_ans_tmp['isTNS_AT'] = _e.find('td',
attrs={
'class': 'cell-isTNS_AT'
}).text.strip()
except Exception:
_ans_tmp['isTNS_AT'] = ''
try:
# <td class="cell-public">Y</td>
_ans_tmp['public'] = _e.find('td',
attrs={
'class': 'cell-public'
}).text.strip()
except Exception:
_ans_tmp['public'] = ''
try:
# <td class="cell-end_prop_period"></td>
_ans_tmp['end_prop_period'] = _e.find(
'td', attrs={
'class': 'cell-end_prop_period'
}).text.strip()
except Exception:
_ans_tmp['end_prop_period'] = ''
try:
# <td class="cell-spectra_count"></td>
_ans_tmp['spectra_count'] = _e.find('td',
attrs={
'class':
'cell-spectra_count'
}).text.strip()
except Exception:
_ans_tmp['spectra_count'] = ''
try:
# <td class="cell-discoverymag">17.775</td>
_ans_tmp['mag'] = _e.find('td',
attrs={
'class': 'cell-discoverymag'
}).text.strip()
except Exception:
_ans_tmp['mag'] = ''
try:
# <td class="cell-disc_filter_name">orange-ATLAS</td>
_ans_tmp['filter'] = _e.find('td',
attrs={
'class':
'cell-disc_filter_name'
}).text.strip()
except Exception:
_ans_tmp['filter'] = ''
try:
# <td class="cell-discoverydate">2019-08-22 06:59:02</td>
_ans_tmp['date'] = _e.find('td',
attrs={
'class': 'cell-discoverydate'
}).text.strip()
except Exception:
_ans_tmp['date'] = ''
try:
# <td class="cell-discoverer">ATLAS_Bot1</td>
_ans_tmp['discoverer'] = _e.find('td',
attrs={
'class': 'cell-discoverer'
}).text.strip()
except Exception:
_ans_tmp['discoverer'] = ''
try:
# <td class="cell-remarks"></td>
_ans_tmp['remarks'] = _e.find('td',
attrs={
'class': 'cell-remarks'
}).text.strip()
except Exception:
_ans_tmp['remarks'] = ''
try:
# <td class="cell-sources"></td>
_ans_tmp['sources'] = _e.find('td',
attrs={
'class': 'cell-sources'
}).text.strip()
except Exception:
_ans_tmp['sources'] = ''
try:
# <td class="cell-bibcode"></td>
_ans_tmp['bibcode'] = _e.find('td',
attrs={
'class': 'cell-bibcode'
}).text.strip()
except Exception:
_ans_tmp['bibcode'] = ''
try:
# self.__log.info(f"_ans_tmp['bibcode']={_ans_tmp['bibcode']}")
_ans_tmp['catalogs'] = _e.find('td',
attrs={
'class': 'cell-ext_catalogs'
}).text.strip()
except Exception:
_ans_tmp['catalogs'] = ''
# add it to the result(s)
if _ans_tmp['tns_id'] != '' and _ans_tmp[
'tns_name'] != '' and _ans_tmp['ra'] != '' and _ans_tmp[
'decl'] != '':
if self.__verbose:
self.__log.debug(f"scraped row {_ans_tmp}")
self.__ans.append(_ans_tmp)
else:
if self.__verbose:
self.__log.debug(f"ignoring {_ans_tmp}")
# +
# method: get_soup()
# -
def get_soup(self, _page=0):
""" scrape web-site page """
# set default(s)
self.__params['page'] = _page if (isinstance(_page, int)
and _page > 0) else 0
if self.__verbose:
self.__log.debug(f'self.__params={self.__params}')
# get request
self.__response = self.get_request()
if self.__verbose:
self.__log.debug(f'self.__response={self.__response}')
# get encoding
_http_encoding = self.__response.encoding if 'charset' in self.__response.headers.get(
'content-type', '').lower() else None
_html_encoding = EncodingDetector.find_declared_encoding(
self.__response.content, is_html=True)
# get soup
self.__soup = None
try:
if self.__verbose:
self.__log.debug(f'Getting soup from self.__response.text')
self.__soup = BeautifulSoup(self.__response.text,
features='html5lib',
from_encoding=(_html_encoding
or _http_encoding))
if self.__verbose:
self.__log.debug(f'Got soup from self.__response.text OK')
except Exception as e:
self.__soup = None
if self.__verbose:
self.__log.error(
f'Failed to get soup from self.__response.text, error={e}')
# +
# method: scrape_tns_pages()
# -
def scrape_tns_pages(self):
""" scrape web-site for tns pages """
# set default(s)
self.__ans = []
self.__pages = -1
self.__total = -1
self.__url = DEFAULT_SEARCH_URL
self.__params = DEFAULT_SEARCH_PARAMS
self.__params['discovered_period_value'] = f'{self.__number}'
self.__params['discovered_period_units'] = f'{self.__unit}'
# get soup
self.get_soup()
if self.__verbose:
self.__log.debug(f'type(self.__soup)={type(self.__soup)}')
# get max number of results by scraping
if self.__soup is not None:
_div = self.__soup.find_all('div', attrs={'class': 'count rsults'})
_ems = [
_e.find_all('em', attrs={'class': 'placeholder'})
for _e in _div
][0]
self.__total = int(_ems[-1].text)
if self.__verbose:
self.__log.debug(f'self.__total={self.__total}')
self.__log.debug(
f"self.__params['num_page']={self.__params['num_page']}")
else:
return self.__total, self.__ans
# calculate pages
self.__pages = math.ceil(
int(self.__total) / int(self.__params['num_page']))
if self.__verbose:
self.__log.debug(f'self.__pages={self.__pages}')
# get record(s) for page 0
self.get_records()
# get record(s) for other pages
if self.__pages > 0:
for _i in range(1, self.__pages):
self.get_soup(_i)
self.get_records()
if self.__verbose:
self.__log.debug(f'sleeping for 5 seconds ...')
time.sleep(5)
# return result
if self.__verbose:
self.__log.debug(f'self.__total = {self.__total}')
self.__log.debug(f'len(self.__ans) = {len(self.__ans)}')
return self.__total, self.__ans
