from juriscraper.lib.date_utils import json_date_handler
from juriscraper.lib.log_tools import make_default_logger
from juriscraper.lib.string_utils import harmonize, clean_string, trunc, CaseNameTweaker
from juriscraper.lib.test_utils import MockRequest
from lxml import html
import re
import requests
from requests.adapters import HTTPAdapter
try:
# Use cchardet for performance to detect the character encoding.
import cchardet as chardet
except ImportError:
import chardet
logger = make_default_logger()
class InsanityException(Exception):
def __init__(self, message):
Exception.__init__(self, message)
class AbstractSite(object):
"""Contains generic methods for scraping data. Should be extended by all
scrapers.
Should not contain lists that can't be sorted by the _date_sort function."""
def __init__(self, cnt=None):
super(AbstractSite, self).__init__()
from juriscraper.lib.date_utils import make_date_range_tuples
from juriscraper.lib.html_utils import (set_response_encoding, clean_html,
fix_links_in_lxml_tree,
get_html_parsed_text)
from juriscraper.lib.log_tools import make_default_logger
from juriscraper.lib.string_utils import convert_date_string
from juriscraper.pacer.utils import (get_pacer_case_id_from_docket_url,
make_doc1_url,
get_pacer_doc_id_from_doc1_url,
get_court_id_from_url,
reverse_goDLS_function, is_pdf)
logger = make_default_logger()
class FreeOpinionReport(object):
"""TODO: document here."""
EXCLUDED_COURT_IDS = [
'casb', 'ganb', 'innb', 'mieb', 'miwb', 'nmib', 'nvb', 'ohsb', 'tnwb',
'vib'
]
VALID_SORT_PARAMS = ('date_filed', 'case_number')
def __init__(self, court_id, pacer_session):
self.court_id = court_id
self.session = pacer_session
super(FreeOpinionReport, self).__init__()
@property
def url(self):