def data(wtext):
infobox_data = {}
for key in wtext_help.data_keys(wtext):
infobox_data[key] = {}
for key in infobox_data:
infobox_data[key]['plain_text'] = parse.get_simple_text(wtext, key)
infobox_data[key]['wiki_links'] = parse.extract_page_links(wtext, key)
infobox_data[key]['raw_text'] = parse.get_simple_text(wtext, key, clean=False)
return infobox_data
def page_name(wtext):
name = parse.get_simple_text(wtext, ['name', 'show_name', 'season_name', 'film name'])
if not name:
name = extract_page_name(wtext)
return clean_help.clean_text(name)
def get_image_filename(wtext):
image_key_list = ['image', 'img', 'cover']
filename = parse.get_simple_text(wtext, image_key_list)
if filename:
filename = filename.replace(' ', '_').encode('utf-8')
if '[[' in filename:
filename = filename.replace('[[', '').replace(']]', '')
if filename.startswith('File:'):
filename = filename.replace('File:', '')
return filename
def get_caption(wtext):
return parse.get_simple_text(wtext, 'caption')
def get_alt(wtext):
return parse.get_simple_text(wtext, 'alt')
