def __init__(self):
HTMLParser.__init__(self)
self.buf = []
self.last_text = []
self.hide_output = False
self.tag_count = 0
self.current_tag = None
def __init__(self):
HTMLParser.__init__(self)
self.links = []
self.in_anchor = False
self.attrs = None
self.title = ''
def __init__(self, baseURL): HTMLParser.__init__(self) self.stack = [] self.anchors = set() self.links = [] self.baseURL = baseURL self.printed = False
def __init__(self, **kwargs):
HTMLParser.__init__(self)
self.kwargs = kwargs
self.active = None
self.last_content = ""
self.rows = []
self.found_first_valid_num = False
def __init__(self, builder=None, encoding=None):
self.__stack = []
if builder is None:
builder = ElementTree.TreeBuilder()
self.__builder = builder
self.encoding = encoding or "iso-8859-1"
HTMLParser.__init__(self)
def __init__(self):
warnings.warn("portage.getbinpkg.ParseLinks is deprecated",
DeprecationWarning, stacklevel=2)
self.PL_anchors = []
html_parser_HTMLParser.__init__(self)
def __init__(self):
HTMLParser.__init__(self)
self.collect_data = False
self.bound = 20
self.des_tag = "div"
self.des_attr = ("id", "content")
self.stations_info = None
def __init__(self):
HTMLParser.__init__(self)
self.state = State.NOWHERE
self.data = ""
self.pnpid = None
self.company = None
self.table = []
def __init__(self):
HTMLParser.__init__(self)
self.url = None
self.params = {}
self.in_form = False
self.form_parsed = False
self.method = "GET"
def __init__(self):
HTMLParser.__init__(self)
self.state = []
self.href= ""
self.obj = {}
self.index = {}
self.done = False
def __init__(self):
HTMLParser.__init__(self)
self.data = dict()
self.recordingAuthor = False
self.recordingBody = False;
self.data["body"] = ""
self.save_tags = ['p', 'blockquote', 'h1', 'h2', 'h3', 'h4', 'h5']
def __init__(self, args):
HTMLParser.__init__(self)
self.root_url = args.URL # Original URL passed.
self.netloc = urllib.parse.urlparse(self.root_url).netloc # Netloc of the URL.
self.depth = args.depth # Distance (pages) to travel.
self.timer = args.time # Amount of time per page.
self.db = MongoClient()[args.db][args.coll] # Database that stores data.
self.sub = args.sub # Subdirectory to set as root of webpage.
self.verbose = args.verbose # Verbosity setting.
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
self.key_terms = ["buy", "sell", "trade", "trading"]
self.count = 0 # Amount of pages processed.
self.posts = 0 # Amount of posts scanned.
self.urlBlacklist = [] # Already completed URLS.
self.urlDNU = [] # Do not use URLS, duplicates.
self.urlList = [self.root_url] # List of URLS to scan.
self.items = [] # Items to look for.
self.discovered = {} # Items discovered + [URLs]
self.BigDict = {} # Dictionary containing ThreadID + [URLS] <- urlDNU list?.
# # # # # # # # # # # # # # # # # # # # #
self.li_main = False # Start of play contribution
self.blockquote_main = False # Start of the message
self.div_quote_main = False # Start of Quote Container
self.div_quote_xpand = False # Start of QuoteExpand
self.blockquote_quote = False # Start of Quote Message
self.text_lock = True # Locks the abilty to print text or use it.
self.li_name = None # Name of original author
self.blockquote_name = None # Name of person being quoted.
# # # # # # # # # # # # # # # # # # #
self.queryDB() # Loads the self.items list.
def __init__(self,strict=False): # Constructor call of parent class. HTMLParser.__init__(self,strict) # Defining variables of this class. # There are 3 types of variables. # data_variables: these are the required information # data_check_variables: boolean values corresponding to each of the data_variables # to keep a check on the data been already extracted or not. # tag_check_variables: used for matching the proper format. self.h1=False self.desc=False self.description=' ' self.sol=False self.solution=' ' self.p=False; self.li=False; self.ref=False; self.references=' ' self.cvss=False; self.cvss_score=0.0; self.cve=False self.cve_id=' ' self.links=[] self.prod=False; self.products=[] self.last_h6=' ' self.h6=False self.h7=False self.clas=False self.attack_from=' ' self.attk=False self.impact=' ' self.impt=False
def __init__(self):
HTMLParser.__init__(self)
self.convert_charrefs = False
self.last = "starttag"
self.in_pre = False
self.output = ""
self.last_tag = ""
def __init__(self, results, url, trackers):
HTMLParser.__init__(self)
self.results = results
self.url = url
self.trackers = trackers
self.td_counter = None
self.current_item = None
def __init__(self, base_href):
HTMLParser.__init__(self)
self.base_href = base_href
self.results = {}
self.group_name = self.group_desc = None
self.in_group_name = self.in_group_desc = self.in_activity = 0
self._clear_info()
def __init__(self, url):
HTMLParser.__init__(self)
self.url = url
self.current_item = None
self.save_data = None
self.seeds_leech = False
self.size_repl = re_compile(",")
def __init__(self, zip_file):
HTMLParser.__init__(self)
self._html = StringIO() # buffer for the processed HTML
self._zip_file = zip_file
# used to exclude the contents of script and object tags
self._excl_nested_level = 0
def __init__(self):
# use a list to store literal bytes and escaped Unicode
if py3:
super().__init__()
else:
HTMLParser.__init__(self)
self.title = []
def __init__(self, strict = False, reps = None, outs = None, sc = True): self.rep = reps self.outStream = outs self.stripComment = sc self.rep.parser = self HTMLParser.__init__(self, strict)
def __init__(self):
"""An overload of the HTML Parser constructor.
We use this initialization code to make sure that every
variable is flushed.
Arguments:
self -- Allows the function to reference parent class
properties. It is unnecessary to specify self during function
calls as it is implied.
"""
# Initialize the HTML Parser.
HTMLParser.__init__(self)
# Initialize the variables.
self._record_name = False
self._record_meal = False
self._record_station = False
self._record_attributes = False
self._day = EMPTY_STRING
self._meal = EMPTY_STRING
self._station = EMPTY_STRING
self._name_text = []
self._station_text = []
self._attributes = []
# Hold all the dining hall menus.
self.menu = []
def __init__(self):
self.foundGo = False
if (sys.version_info.minor < 4):
HTMLParser.__init__(self)
else:
self.html_parser_init_kwargs = { 'convert_charrefs' : True }
HTMLParser.__init__(self, **self.html_parser_init_kwargs)
def __init__(self,
remove_comments=False,
remove_empty_space=False,
remove_all_empty_space=False,
reduce_empty_attributes=True,
reduce_boolean_attributes=False,
remove_optional_attribute_quotes=True,
keep_pre=False,
pre_tags=PRE_TAGS,
pre_attr='pre'):
if sys.version_info[0] >= 3 and sys.version_info[1] >= 4:
# convert_charrefs is True by default in Python 3.5.0 and newer. It was
# introduced in 3.4.
HTMLParser.__init__(self, convert_charrefs=False)
else:
HTMLParser.__init__(self)
self.keep_pre = keep_pre
self.pre_tags = pre_tags
self.remove_comments = remove_comments
self.remove_empty_space = remove_empty_space
self.remove_all_empty_space = remove_all_empty_space
self.reduce_empty_attributes = reduce_empty_attributes
self.reduce_boolean_attributes = reduce_boolean_attributes
self.remove_optional_attribute_quotes = remove_optional_attribute_quotes
self.pre_attr = pre_attr
self._data_buffer = []
self._in_pre_tag = 0
self._in_head = False
self._in_title = False
self._after_doctype = False
self._tag_stack = []
self._title_newly_opened = False
self.__title_trailing_whitespace = False
def __init__(self): HTMLParser.__init__(self) self.items = [] self.foundItem = False self.br_before = False self.checkBr = False self.current_item_url = ""
def __init__(self,
remove_comments=False,
remove_empty_space=False,
remove_all_empty_space=False,
reduce_empty_attributes=True,
reduce_boolean_attributes=False,
remove_optional_attribute_quotes=True,
keep_pre=False,
pre_tags=PRE_TAGS,
pre_attr='pre'):
HTMLParser.__init__(self)
self.keep_pre = keep_pre
self.pre_tags = pre_tags
self.remove_comments = remove_comments
self.remove_empty_space = remove_empty_space
self.remove_all_empty_space = remove_all_empty_space
self.reduce_empty_attributes = reduce_empty_attributes
self.reduce_boolean_attributes = reduce_boolean_attributes
self.remove_optional_attribute_quotes = remove_optional_attribute_quotes
self.pre_attr = pre_attr
self._data_buffer = []
self._in_pre_tag = 0
self._in_head = False
self._in_title = False
self._after_doctype = False
self._tag_stack = []
self._title_newly_opened = False
self.__title_trailing_whitespace = False
def __init__(self, news): HTMLParser.__init__(self) self.count_a = 0; self.current_tag = "" self.looking_for_testata = False self.news = news
def __init__(self):
HTMLParser.__init__(self)
self.links = []
self.isNumber = 0
self.stack = []
self.day = []
self.test = []
def __init__(self):
HTMLParser.__init__(self)
self.starParsing = False
self.ratingParsing = False
self.starStack = Stack()
self.ratingStack = Stack()
self.ratingDict = {}
def __init__(self):
HTMLParser.__init__(self)
self.stack = []
self.template_names = []
self.templates = {}
self.current_template = ""
self.current_template_count = 0
def __init__(self): self.urlList = [] self.index = 0 self.nextUrl = '' self.tagList = ['li','a'] self.classList = ['photo-list-padding','pic'] HTMLParser.__init__(self)
def __init__(self):
HTMLParser.__init__(self)
self.recording = 0
self.data = []
self.link = ""
def __init__(self, allows=[]):
HTMLParser.__init__(self)
self.allow_tags = allows if allows else self.allow_tags
self.result = []
self.start = []
self.data = []
def __init__(self):
HTMLParser.__init__(self)
self.title = None
def __init__(self):
HTMLParser.__init__(self)
self.reset()
self.fed = []
def __init__(self, **kw):
HTMLParser.__init__(self, **kw)
self._fed = []
def __init__(self):
HTMLParser.__init__(self)
self.reset()
self.HTMLDATA = []
def __init__(self):
HTMLParser.__init__(self)
self.AllLinks = []
def __init__(self):
HTMLParser.__init__(self)
self._texts = [] # type: list
self._ignore = False
def __init__(self):
HTMLParser.__init__(self)
self.first_row = True
self.in_cell = False
self.links = []
def __init__(self):
HTMLParser.__init__(self)
self.json_link = None
def __init__(self):
BaseHTMLParser.__init__(self, convert_charrefs=False)
def __init__(self, ostream):
HTMLParser.__init__(self)
self.in_pre = False
self.in_code = False
self.ostream = ostream
self.pygments_fix = False
def __init__(self):
HTMLParser.__init__(self)
self.title = ""
self.is_title = False
self.content = ""
self.is_content = False
def __init__(self):
HTMLParser.__init__(self)
self.out_buffer = []
def __init__(self):
HTMLParser.__init__(self)
self.__text = []
def __init__(self):
HTMLParser.__init__(self)
self.content = ""
self.is_content = False
self.other_content = False
self.skip = False
def __init__(self):
HTMLParser.__init__(self)
self.flag = 0
self.endflag = 0
self.divflag = False
def __init__(self):
HTMLParser.__init__(self)
self.content = None
self.content_type = self.UNKNOWN
def __init__(self):
HTMLParser.__init__(self)
self.strings = []
def __init__(self):
HTMLParser.__init__(self)
self.tag_results = {}
def __init__(self, tag="", attrs=None):
# Initiate HTMLParser
HTMLParser.__init__(self)
self.convert_charrefs = True
self._root = None # root element
self._data = [] # data collector
self._factory = Etree.Element
self.enabled = not tag
self._unw_attrs = []
self.tag = tag
# Split attributes into wanted and unwanted attributes
if attrs:
self.attrs = attrs
for key, value in attrs.copy().items():
if value == 0:
self._unw_attrs.append(key)
del attrs[key]
else:
self.attrs = {}
# Some tags in html do not require closing tags so thoes tags will need to be auto closed (Void elements)
# Refer to: https://www.w3.org/TR/html/syntax.html#void-elements
self._voids = frozenset((
"area",
"base",
"br",
"col",
"hr",
"img",
"input",
"link",
"meta",
"param",
# Only in HTML5
"embed",
"keygen",
"source",
"track",
# Not supported in HTML5
"basefont",
"frame",
"isindex",
# SVG self closing tags
"rect",
"circle",
"ellipse",
"line",
"polyline",
"polygon",
"path",
"stop",
"use",
"image",
"animatetransform"))
# Create temporary root element to protect from badly written sites that either
# have no html starting tag or multiple top level elements
elem = self._factory("html")
self._elem = [elem]
self._last = elem
self._tail = 0
def __init__(self):
HTMLParser.__init__(self)
self.a = []
self.n = []
self.x = 0
def __init__(self,date_url_file):
HTMLParser.__init__(self)
self.tag = None
self.date_url = False
self.href = None
self.date_url_file = date_url_file
def __init__(self):
HTMLParser.__init__(self)
self.content = []
self.in_div = False
def __init__(self, druid_module_name, compatible_license_names):
HTMLParser.__init__(self)
self.state = "none"
self.druid_module_name = druid_module_name
self.compatible_license_names = compatible_license_names
def __init__(self):
HTMLParser.__init__(self)
self.div = False
self.div_2 = False
self.cpt = 0
self.resulte = ""
def __init__(self):
HTMLParser.__init__(self)
self.maxword = 150
def __init__(self):
HTMLParser.__init__(self)
def __init__(self, tag_to_analyse='div'):
HTMLParser.__init__(self)
self.tag_to_analyse = tag_to_analyse
self.classes = {}
def __init__(self, base, output=None):
HTMLParser.__init__(self)
if output is None:
output = []
self.output = output
self.base = base
