def __init__(self, db):
PostImporter.__init__(self, db)
config_parser = getConfig()
self.start_date = config_parser.eval("DEFAULT", "start_date")
self.end_date = config_parser.eval("DEFAULT", "end_date")
self._data_folder = self._config_parser.eval(self.__class__.__name__,
"data_folder")
def __init__(self, db):
PostImporter.__init__(self, db)
self._max_number_of_threads = self._config_parser.eval(
self.__class__.__name__, "max_number_of_threads")
self._shorten_url_expended_url_dict = {}
self._destination_url_source_url_dict = {}
self.resolved_urls = []
def __init__(self, db):
PostImporter.__init__(self, db)
self._db = db
self._twitter_crawler = Generic_Twitter_Crawler(db)
self._missing_data_complementor = MissingDataComplementor(db)
self._original_tsv_location = self._config_parser.eval(
self.__class__.__name__, "original_tsv_location")
self._limit_per_crawl = self._config_parser.eval(
self.__class__.__name__, "limit_per_crawl")
self._post_label_dict = {}
self._start_len = len(self._post_label_dict.keys())
self._num_of_rows_in_dataset = 0
self._post_author_to_label_dict = {}
chrome_options = Options()
chrome_options.add_argument(
"--headless") # to make the process run in background
self._web_driver = selenium.webdriver.Chrome(
executable_path=r'vendors\chromedriver\chromedriver.exe',
chrome_options=chrome_options)
# statistics vars
self._counter = 0
self._more_than_one = 0
self._exactly_one = 0
self._loggin_processed = 0
def __init__(self, db):
PostImporter.__init__(self, db)
self._past_hours = self._config_parser.eval(self.__class__.__name__,
"past_hours")
self._author_name_as_domain = self._config_parser.eval(
self.__class__.__name__, "author_name_as_domain")
self._author_classify_dict = {}
self._author_prop_dict = {}
def __init__(self, db):
PostImporter.__init__(self, db)
config_parser = getConfig()
self.xmlPath = config_parser.get(self.__class__.__name__, "xml_path")
# self.xmlPath = configInst.get(self.__class__.__name__,"XMDL_source_path")
self.fileName = None
self.CurrFolderPath = None
def __init__(self,db):
PostImporter.__init__(self,db)
configInst = getConfig()
self.source_path = configInst.get(self.__class__.__name__,"FDL_source_path")
self.file_date_format = configInst.get(self.__class__.__name__,"date_format")
self.fileName = None #@review: not a field. make it local variable.
self.URLforUnittest = None #@review: no code should be written especially for unittests (except the tests)
self.CurrFolderPath = None #@review: coding convention: small letter field names and _ for private members
def __init__(self, db):
PostImporter.__init__(self, db)
config_parser = getConfig()
self.start_date = config_parser.eval("DEFAULT", "start_date")
self.end_date = config_parser.eval("DEFAULT", "end_date")
self._data_folder = self._config_parser.eval(self.__class__.__name__,
"data_folder")
self._bad_actor_threshold = self._config_parser.eval(
self.__class__.__name__, "bad_actor_threshold")
self._optional_classes = self._config_parser.eval(
self.__class__.__name__, "optional_classes")
self._author_classify_dict = {}
def __init__(self, db):
# politifact posts title are biased, dont use them as features
PostImporter.__init__(self, db)
self._domain = u"PolitiFact"
self._subjects = self._actions = self._config_parser.eval(
self.__class__.__name__, "subjects")
self._posts_per_subject = self._actions = self._config_parser.eval(
self.__class__.__name__, "posts_per_subject")
self._post_types = self._actions = self._config_parser.eval(
self.__class__.__name__, "post_types")
self._author_classify_dict = {}
self._author_prop_dict = {}
self._post_type_dict = {}
def __init__(self, db):
PostImporter.__init__(self, db)
self._author_name_as_domain = self._config_parser.eval(
self.__class__.__name__, "author_name_as_domain")
self._retrieve_news_by_keywords = self._config_parser.eval(
self.__class__.__name__, "retrieve_news_by_keywords")
self._num_of_top_terms = self._config_parser.eval(
self.__class__.__name__, "num_of_top_terms")
self._filter_sentences = self._config_parser.eval(
self.__class__.__name__, "filter_sentences")
self._topic_term_manager = Topic_Term_Manager(db)
self._characters_to_add_to_unstemmed_words = [
'e', 'able', 'al', 'ial'
'ion', 'ing', 'er', 'ies'
]
def __init__(self, db):
PostImporter.__init__(self, db)
self._input_csv_file = self._config_parser.eval(self.__class__.__name__, "input_csv_file")
# There is no author so the website would be the author. We should not include this author in the analysis.
self._author_name = unicode("snopes")
def __init__(self, db):
PostImporter.__init__(self, db)
self._data_folder = self._config_parser.eval(self.__class__.__name__,
"data_folder")
def execute(self, window_start=None):
logging.info("execute")
logging.info("PostImporter.execute(self, window_start)")
PostImporter.execute(self, window_start)
def __init__(self, db):
PostImporter.__init__(self, db)
self._path_to_file = self._config_parser.eval(self.__class__.__name__,
"path_to_file")