def __init__(self, site_url, html):
language_table = stats_lib.set_up_character_ranges_table()
tags = gt.get_tags(html)
self.title = gt.get_title( tags )
self.outgoing_links = gt.get_links(site_url, tags)
self.outgoing_link_count = len( self.outgoing_links )
self.scripts = gt.get_scripts(tags)
self.number_of_scripts = len(self.scripts)
self.langs = dict()
self.alphabets_on_site = []
self.incoming_link_count = 0
text = tags.getText()
#print( text)
for ch in text:
lang = stats_lib.check_ranges_from_table( ch ,language_table )
#print( ch , lang )
if lang in self.langs:
self.langs[lang] += 1
else:
self.langs[lang] = 1
for key in self.langs:
if self.langs[key] > len(text)/100 and key not in self.alphabets_on_site:
self.alphabets_on_site.append(key)
def all_alphabets(robot):
import stats_lib
language_table = stats_lib.set_up_character_ranges_table()
cursor = robot.get_data_from_table('fish_sites', 'url,body_text')
alphabets = dict()
for row in cursor:
text = row[1]
url = row[0]
langs = dict()
for ch in text:
lang = stats_lib.check_ranges_from_table( ch, language_table )
#print( ch , lang )
if lang in langs:
langs[lang] += 1
else:
langs[lang] = 1
for key in langs:
if langs[key] > len(text)/50.0:
if key not in alphabets:
alphabets[key] = 1
else:
alphabets[key] += 1
robot.close_connection()
return alphabets
def __init__(self, site_url, html):
language_table = stats_lib.set_up_character_ranges_table()
tags = gt.get_tags(html)
self.url = site_url
self.title = gt.get_title( tags )
self.outgoing_links = gt.get_links(site_url, tags)
self.outgoing_link_count = len( self.outgoing_links )
self.scripts = gt.get_scripts(tags)
self.number_of_scripts = len(self.scripts)
self.langs = dict()
self.hash = make_hash(site_url)
self.alphabets_on_site = []
for script in tags(['script', 'style']):
script.extract()
self.body = strip_non_space_whitespace( tags.getText() )
text = self.body
#print( text)
for ch in text:
lang = stats_lib.check_ranges_from_table( ch, language_table )
#print( ch , lang )
if lang in self.langs:
self.langs[lang] += 1
else:
self.langs[lang] = 1
for key in self.langs:
if self.langs[key] > len(text)/70 and key not in self.alphabets_on_site:
self.alphabets_on_site.append(key)
self.n_grams = stats_lib.count_n_grams( self.body, 5 )
self.symbol_freq = stats_lib.count_symbol_frequency( self.body )
self.symbol_entropy = stats_lib.calculate_symbol_entropy( self.symbol_freq )
self.raw_html = html
