def __init__(self, input_url):
self.input_url = input_url
print "INIT INPUT URL:", self.input_url
self.base_url = c_m.mk_url_base(self.input_url) # home_page
print "INIT BASE URL:", self.base_url
self.domain = c_m.strip_to_domain(self.base_url)
print "INIT DOMAIN:", self.domain
# base paths:
self.static_part_path = "site_data\\"
self.pc_specific_part_path = os.path.dirname(
os.path.realpath(__file__)) + "\\"
self.main_path = self.pc_specific_part_path + self.static_part_path
print "INIT MAIN PATH:", self.main_path
# dynamic part path:
self.domain_folder_name = self.domain + u"\\"
self.domain_folder_path = self.main_path + self.domain_folder_name
self.page_list_f_name = u"page_list.txt" #site pages' data and data file names destination
self.page_list_path = self.main_path + self.domain_folder_name + self.page_list_f_name
# module specific paths
self.html_folder_name = u"html\\" # retrieved html ouput files folder
self.text_folder = u"text\\" # output unique text files folder
self.eng_text_folder = u"text_eng\\" # translated text output files folder
self.text_folder_path = self.domain_folder_path + self.text_folder
self.text_eng_folder_path = self.domain_folder_path + self.eng_text_folder
def laod_tabs(self, adjusted_page_list, eng_text):
""" From or according to adjusted page list data
sets needed variable values,
retrieves original or english page texts,
loads tabs with apropriate data in place"""
print "IN: laod_tabs"
for ind in range(len(adjusted_page_list)):
#laod_tabs: setting variables
base_url = adjusted_page_list[0][1]
url_domain = c_m.strip_to_domain(base_url)
domain_folder = url_domain + "\\"
page_link_url = adjusted_page_list[ind][1]
active_link_url_no_domain = page_link_url.replace(base_url,'')
active_link_url_no_domain = self.fit_links_to_50(active_link_url_no_domain)
print "laod_tabs: TEST ---------------- active_link_url_no_domain %r" % active_link_url_no_domain
self.active_link_url_no_domain_list.append(active_link_url_no_domain)
active_tab = self.t_tab_list[ind]
#laod_tabs: method supports original and english page text loading set as input for method
if eng_text:
folder_type = "text_eng\\"
page_text_f_name = adjusted_page_list[ind][4]
else:
folder_type = "text\\"
page_text_f_name = adjusted_page_list[ind][3]
page_text_f_path = self.main_path + domain_folder + folder_type + page_text_f_name
#laod_tabs: LOADING TEXT FROM FILE
self.noteb.add(active_tab, text='%s' % (active_link_url_no_domain)) #laod_tabs: tab header text
#laod_tabs: INSERTING HYPERLINK TO TAB TEXT WIDGET
hyper_page_link = page_link_url + '\n\n' #laod_tabs: empty line between hyperlink and text
active_tab.insert(END, hyper_page_link)
#laod_tabs: RETRIEVING PAGE TEXT FROM FILE
page_text = c_m.simply_read(page_text_f_path)
#laod_tabs: INSERTING PAGE TEXT TO TAB TEXT WIDGET
active_tab.insert(END, page_text) #laod_tabs: Adding retrieved text to notebook text window
#laod_tabs: CONFIGURING INSERTED LINK TO SHOW UP AS PROPER HYPERLINK
active_tab.tag_add('hyper', '1.0', '1.%d' % len(page_link_url))
active_tab.tag_config('hyper', foreground='blue')
active_tab.tag_bind('hyper', "<Enter>", lambda event, arg=ind: self.mouse_on(event, arg))
active_tab.tag_bind('hyper', "<Leave>", lambda event, arg=ind: self.mouse_of(event, arg))
active_tab.tag_bind('hyper', "<Button-1>", lambda event, arg=page_link_url: self.hyper(event, arg))
#TEST FUNCTIONALITY: if keyword present make the tab visible in GUI
page_key_word = ["Om-oss", "om-oss", "om oss", "OM-OSS"]
if (page_key_word[0] or page_key_word[1] or page_key_word[2] or page_key_word[3]) in page_link_url:
self.noteb.select(active_tab)
def mk_tabs_data_set(self, site_data_entry):
"""According to site data from 1_ready_for_veri file
retrieves page data from page_list file,
places homepage as first tab,
sorts other according to page text symbol count from biggest down"""
print "mk_tabs_data_set: RETRIEVING AND REARANGING PAGE LIST ENTRY DATA"
base_url = site_data_entry[3]
page_list_f_name = 'page_list.txt'
url_domain = c_m.strip_to_domain(base_url) # domain acts as key in filesystem composed of folders named as domains
print "FOR DOMAIN: ", url_domain
domain_folder = url_domain + "\\"
page_list_path = self.main_path + domain_folder + page_list_f_name
page_list = c_m.l_of_l_read(page_list_path)
print "mk_tabs_data_set: ADJUSTING PAGE LIST"
adjusted_page_list = self.mk_adjusted_page_list(page_list) # sorting list according to unique page text length
return adjusted_page_list