async def wikilang(ctx, language=None):
if language == None:
deflang = str(
wikipedia_language.setdefault(
str(ctx.message.author.id),
guild_language.get(str(ctx.guild.id), "en")))
await ctx.send("Language is {short} - {long}".format(
short=deflang, long=wikipedia.languages()[deflang]))
return
query = language.lower()
if query in wikipedia.languages():
wikipedia_language.update({str(ctx.message.author.id): str(query)})
lg = wikipedia.languages()[query]
await ctx.send(languages[guild_language.setdefault(
str(ctx.guild.id), "en")]["wikilang_success"].format(query=query,
lg=lg))
else:
defaultlanguage = wikipedia_language.setdefault(
str(ctx.message.author.id),
guild_language.setdefault(str(ctx.guild.id), "en"))
await ctx.send(languages[guild_language.setdefault(
str(ctx.guild.id), "en")]["wikilang_error"].format(
defaultlang=defaultlanguage,
defaultlg=wikipedia.languages()[defaultlanguage]))
with open('wikipedia_language.json', 'w') as json_file:
json.dump(wikipedia_language, json_file)
if use_postgres: backup()
def _is_parameters_ok(self):
"""
Check if received parameters are ok to perform operations in the neuron
:return: true if parameters are ok, raise an exception otherwise
.. raises:: InvalidParameterException
"""
if self.query is None or self.query == "":
raise InvalidParameterException("Wikipedia needs a query")
if self.language is None:
raise InvalidParameterException("Wikipedia needs a language")
valid_language = wikipedia.languages().keys()
if self.language not in valid_language:
raise InvalidParameterException(
"Wikipedia needs a valid language: %s" % valid_language)
if self.sentences is not None:
try:
self.sentences = int(self.sentences)
except ValueError:
# Handle the exception
raise InvalidParameterException(
"Number of sentences must be an integer")
return True
def wiki_extraction(n, languages):
for lan in languages:
if lan not in w.languages():
raise Exception('Language wrongly specified')
if isinstance(lan, str) is False:
raise Exception(
'Wrong format. The language list takes only strings')
rows_list = []
for lan in languages:
w.set_lang(lan)
page = w.random(pages=n)
for i in page:
try:
dict_ = {}
summary = w.WikipediaPage(title=i).summary
if len(summary) > 0:
input_dict = {'Title': i, 'Text': summary, 'Language': lan}
dict_.update(input_dict)
rows_list.append(dict_)
else:
page.append(w.random(pages=1))
except:
page.append(w.random(pages=1))
pass
return pd.DataFrame(rows_list)
def choose_language():
user_input = input("[1]. Wpisz kod WP swojego języka(en, pl, de, etc.)\n"
"[2]. Wybierz język z listy\n")
language_choosen = False
languages = wikipedia.languages()
if user_input == '1':
while not language_choosen:
wp_code = input("Wpisz kod: ")
if wp_code in languages:
wikipedia.set_lang(wp_code)
language_choosen = True
else:
print("Nie istnieje taki kod!")
else:
show_languages(languages)
while not language_choosen:
search_language = input("Podaj język: ")
if search_language in languages.values():
for wp, lang in languages.items():
if lang == search_language:
wikipedia.set_lang(wp)
language_choosen = True
else:
print("Nie ma takiego języka")
os.system('clear')
def busca_idioma(i):
try:
while not i in wikipedia.languages():
i = input("Input no válido: ")
return i
except:
print("MALA CONEXIÓN.")
def busca_idioma(i):
try:
while not i in wikipedia.languages():
i = input("Input no válido: ")
return i
except:
print("FALLO AL ESTABLECER EL IDIOMA")
def activate(self):
super().activate()
if self.config['LANGUAGE'] in wikipedia.languages():
wikipedia.set_lang(self.config['LANGUAGE'])
else:
self.log.warning('{0} is not a valid language code.'.format(
self.config['LANGUAGE']))
return
def busca_idioma():
i = input(
"Introduce iniciales del idioma deseado (ej: \'es\',\'en\',\'fr\'...): "
)
try:
while not i in wikipedia.languages():
i = input("Input no válido: ")
return i
except:
print("FALLO AL ESTABLECER EL IDIOMA")
def wiki_lang(lang, set_id):
langs_dict = wikipedia.languages()
if lang in langs_dict.keys():
wiki_settings[set_id] = lang
return ("Language has been changed to {} successfully.".format(
langs_dict[lang]))
return ("{} not available!\n"
"See meta.wikimedia.org/wiki/List_of_Wikipedias for "
"a list of available languages, and use the prefix "
"in the Wiki column to set the language.".format(lang))
def setLanguage():
print('Languages availables: ')
languages = wikipedia.languages()
for lang in languages:
print(f'{lang} : {languages[lang]}')
selected_lang = input('(*) Option (default = en): ')
if (selected_lang):
global language
language = selected_lang
def home():
lang = wikipedia.languages()
languages = []
for i in lang:
languages.append(wikipedia.languages()[i])
if request.method == "POST":
try:
query = request.form.get('query')
try:
result = wikipedia.summary(query)
except wikipedia.exceptions.DisambiguationError:
stra = "There May Be Multiple Articles About The Topic "
strb = ". Please Be More Specific!"
result = stra + query + strb
return render_template("index.html", result=result)
except:
pass
return render_template("index.html", languages=languages)
async def wikipedia(self, ctx, language: str):
"""Wikipedia based command. Do !help wp."""
global wiki_lang
if language in wikipedia.languages():
wiki_lang = language
wikipedia.set_lang(language)
else:
error_d = f'"{language}" isn\'t in the list of languages.'
await ctx.send(embed=error_embed(error_d))
if ctx.invoked_subcommand is None:
error_d = 'this is a f****n subcommand, idiot. can\'t you just do !help wp or something?'
await ctx.send(embed=error_embed(error_d))
async def wiki(msg: types.Message):
_lang = [msg.from_user.language_code if msg.from_user.language_code else 'en-us']
regex_groups = re.findall(r'(\w{2})\.wikipedia.org\/wiki\/([\S]{0,})', msg.text)
if not regex_groups[0][0] in wikipedia.languages():
return await msg.reply(_lang['lang_not_found'])
wikipedia.set_lang(regex_groups[0][0])
try:
page = wikipedia.page(regex_groups[0][1])
await msg.reply(f"<b>{page.title}</b>\n{page.summary}")
except:
return await msg.reply(_lang["page_not_found"])
def __init__(self, query=None, lang="en"): self.name = "" self.text = "" self.dates = [] self.images = [] self.picture = "" self.hits = [] if not query: return self.query = query if lang in wikipedia.languages(): wikipedia.set_lang(lang)
def check_wiki_link_command(self, comment):
'''
Функция проверки на команду краткого содержания по ссылке на статью википедии
comment - комментарий для проверки
return True - найдена команда в нужном формате и успешно отправлен ответ
return False - не найден либо ошибка при ответе
'''
history_filename = os.path.join(self.bot_profile, self.WIKI_LOG_PATH)
if not os.path.exists(history_filename):
open(history_filename, 'w').close()
history_file = open(history_filename, 'r')
if comment.id not in history_file.read().splitlines():
match = re.findall('.*\[\[(http[s]?:\/\/([a-z]{1,3})\.wikipedia\.org\/wiki\/.+)\]\].*', comment.body)
if match:
self.write_to_log('Вики-ссылка найдена в комментарии с id: ' + comment.id)
url = match[0][0] # ссылка на статью
lang = match[0][1] # языковой поддомен
if lang not in wikipedia.languages():
self.write_to_log('Дан неверный языковой поддомен "' + lang + '" в ссылке ' + url)
return False
try:
page_title = self.get_wiki_page_title(url)
wikipedia.set_lang(lang)
summary = self.WIKI_HEADER + wikipedia.summary(page_title) + self.WIKI_FOOTER
except wikipedia.exceptions.DisambiguationError as e:
summary = self.WIKI_DISAMB_REPLY
for possible_title in e.options:
summary+= possible_title + '\n\n'
except Exception as e:
print('Возникло исключение: ' + str(e) + '\n')
history_file.close()
return False
comment.reply(summary)
history_file.close()
history_file = open(history_filename, 'a+')
history_file.write(comment.id + '\n')
history_file.close()
self.write_to_log('Успешно отправил ответ на вики-команду и записал в историю, таймаут ' + str(self.RESPONCE_TIMEOUT) + ' сек.')
time.sleep(self.RESPONCE_TIMEOUT)
return True
else:
history_file.close()
return False
else:
history_file.close()
self.write_to_log('Повтор комментария, можно не отвечать')
return True
def do_activate(self, args, argv):
lang = args[0]
langTrue = str(lang) in wikipedia.languages()
if langTrue == True:
wikipedia.set_lang(str(lang))
print(wikipedia.summary(' '.join(args[1:]), sentences=3))
else:
if not re.search(lang, "[a-z][a-z]+"):
print(
"'" + str(lang) +
"' not found as language, trying to find a summary in the english language"
)
wikipedia.set_lang("en")
print(wikipedia.summary(' '.join(args[1:]), sentences=3))
else:
wikipedia.set_lang("en")
print(wikipedia.summary(' '.join(args), sentences=3))
def wikiSearch(lang="indonesia", seq="Test", *args):
"""Search for a specific subject on wikipedia and returns its title, summary, and link in a list.
If your search query return multiple search results, this function will return a tuple of the error name and a list of top 5 search results."""
if type(lang) is not str and type(seq) is not str: raise TypeError('language and search query must be a string.')
for _, ls in enumerate(list(wapi.languages().items())):
if lang in ls[1].lower():
lang = ls[0]
break
try:
wapi.set_lang(lang)
page = wapi.page(seq)
except wapi.exceptions.DisambiguationError as err:
return ('error', err.args[1][:5])
return [page.title, wapi.summary(seq).split('\n')[0][:1000]+'..', page.url]
async def lang(ctx):
global current_language
msg = ctx.message.content.split(" ")
command = msg[2]
langcodes = wikipedia.languages().keys()
#Check which command to run
if command == "list" or command == "List":
#List of most used languages on wikipedia
languagelist = "English / English = en\nCebuano / Sinugboanong = ceb\nSwedish / Svenska = sv\nGerman / Deutsch = de\nFrench / Français = fr\nDutch / Nederlands = nl\nRussian / Русский = ru\nItalian / Italiano = it\nSpanish / Español = es\nWaray-Waray / Winaray = war\nPolish / Polski = pl\nVietnamese / Tiếng Việt = vi\n Japanese / 日本語 = ja\n"
languagelistwiki = "https://meta.wikimedia.org/wiki/List_of_Wikipedias"
embed = discord.Embed(
title="Wikipedia language list:",
color=0,
description=languagelist +
"\n\nAll supported languages can be found [here]({})".format(
languagelistwiki))
embed.set_thumbnail(
url=
"https://www.wikipedia.org/static/images/project-logos/{}wiki.png".
format(current_language))
await bot.say(embed=embed)
elif command == "set" or command == "Set":
#Check if the given language(langcode) is valid
if msg[3] in langcodes:
current_language = msg[3]
wikipedia.set_lang(msg[3])
else:
embed = discord.Embed(
title="Languages not found:",
color=0xe74c3c,
description=
"Sorry, the language '{}' was not found. Please run '/w lang list' to see all language codes."
.format(msg[3]))
embed.set_thumbnail(
url=
"https://www.wikipedia.org/static/images/project-logos/{}wiki.png"
.format(current_language))
await bot.say(embed=embed)
def send_welcome(message):
title = ''.join(message.text.split(" ")[1:])
if title in wikipedia.languages():
wikipedia.set_lang(title)
bot.send_message(
chat_id=message.chat.id,
text='set up %s language'%title
)
else:
# bot.send_message(
# chat_id=message.chat.id,
# text=str('1' + lan_str)
# )
bot.send_message(
chat_id=message.chat.id,
# text=str('wrong language flag "%s" use on of %s'%(str(title)),lan_str)
# text=str('wrong language flag "%s" use on of %s'%('1','lan_str'))
text=str('wrong language flag')
)
def _is_parameters_ok(self):
"""
Check if received parameters are ok to perform operations in the neuron
:return: true if parameters are ok, raise an exception otherwise
.. raises:: InvalidParameterException
"""
if self.query is None:
raise InvalidParameterException("Wikipedia needs a query")
if self.language is None:
raise InvalidParameterException("Wikipedia needs a language")
valid_language = wikipedia.languages().keys()
if self.language not in valid_language:
raise InvalidParameterException(
"Wikipedia needs a valid language: %s" % valid_language)
return True
def execute_wiki(query, client, message):
if "/comune" in query:
try:
return comune(client, message)
except:
id_messaggio = utils.get_config.get_id_msg(message)
client.edit_message_text(utils.get_config.get_chat(message),
id_messaggio + 1, "Operazione fallita")
return
lingua = get_lang(query)
if not (lingua in wikipedia.languages()) or lingua == "all":
return exec_wiki_ita(query, client, message)
word = get_keyword(query)
if " all " in query:
return wikiall(word, client, message, lingua)
if "random" in query:
return wikirandom(1, False, client, message, lingua)
else:
return wiki(word, client, message, lingua)
def __init__(self, parent=None):
QWidget.__init__(self, parent)
self.setupUi(self)
self.about_action.setIcon(QIcon('images/about.png'))
self.preferences_action.setIcon(QIcon('images/preferences.png'))
self.quit_action.setIcon(QIcon('images/quit.png'))
self.quit_action.triggered.connect(lambda : exit(0))
self.preferences_action.triggered.connect(self.handle_preferences_menu_action)
self.title_line_edit.returnPressed.connect(self._extract_from_wiki)
self.content_text_browser.anchorClicked.connect(self.handle_anchor_clicked)
self.run_push_button.clicked.connect(self.handle_run_button)
self.run_push_button.setIcon(QIcon('images/run.png'))
self.run_push_button.setText('Download')
self.setWindowIcon(QIcon('images/copas-logo.png'))
self.page_combo_box.addItems(
['Content', 'Images', 'Summary', 'Images Links', 'References Links'])
self.about_action.triggered.connect(self.handle_about_menu_action)
for lang in sorted(wikipedia.languages()):
self.lang_combo_box.addItem(lang)
async def wikipedia(self, context, lang: str = None, query: str = None):
''' Get a page from wikipedia and reply with an embed '''
query = self.bot.get_text(context)
if lang is not None:
if lang.startswith('(') and lang.endswith(')'):
query = query[len(lang) + 1:]
lang = lang[1:-1]
else:
lang = None
if query in [None, '', ' ']:
await self.bot.doubt(context)
return
try:
import wikipedia
if lang is not None and lang in wikipedia.languages().keys():
wikipedia.set_lang(lang)
else:
wikipedia.set_lang('en')
page = wikipedia.page(query)
summary = page.summary
if len(summary) > 1222: # totally arbitrary chosen number
summary = summary[:1220] + '...'
embed = discord.Embed(title=page.title,
description=summary,
url=page.url)
embed.set_footer(text=page.url)
if self.bot.config['bleeding']:
if len(page.images) > 0:
embed.set_image(url=page.images[0])
await self.bot.say(embed=embed)
await self.bot.replied(context)
except wikipedia.PageError as e:
await self.bot.reply(
'{}\nMake sure you search for page titles in the language that you have set.'
.format(e))
await self.bot.doubt(context)
except KeyError:
pass
except wikipedia.DisambiguationError as e:
msg = '```\n{}\n```'.format(e)
await self.bot.doubt(context)
await self.bot.say(msg)
def dsply_lang(self):
try:
self.tex_name.setText("Supported languages")
content="Wikipedia provides content in the following languages\n"
list_of_languages=wiki.languages().values()
for lenguiz in list_of_languages:
content+=str(str(lenguiz)+"\n")
self.box_cont.setPlainText(content)
self.box_smry.clear()
self.box_sgst.clear()
self.val_paid.setText("UNDEFINED")
self.val_reid.setText("UNDEFINED")
self.head_cont.setText("Wisdom currently supports only English language")
self.art_url_disp.setText("An language page has no URL")
except Exception as e:
self.tex_name.setText("Supported languages")
self.head_cont.setText("Failed to retrieve the list of supported languages")
self.box_smry.clear()
self.box_cont.clear()
self.box_sgst.clear()
self.val_paid.setText("UNDEFINED")
self.val_reid.setText("UNDEFINED")
self.art_url_disp.setText("An errored page has no URL")
def wikispam():
while True:
selectedlang = input(
"Choose the language you want to spam using the UTF-8 Language Codes ex.English - en:\n"
)
try:
if selectedlang not in wikipedia.languages():
if selectedlang != wikipedia.languages():
print(
f"Your selected Language of {selectedlang} is not found. Try again!\n"
)
continue
break
except:
print("This is not a language code")
print(
f"You selected the language {selectedlang} for your Wikipedia article!"
)
while True:
timer = input(
"\nHow long do you want the time in between messages to be (sec)?\nChoose a number: "
)
try:
float(timer)
if float(timer) < -0.1:
print("This is not a valid number!")
continue
break
except ValueError:
print("This is not a valid number!\n")
print(
f"\nYou opened a random wiki article with a timer of {timer} seconds!\nBe sure to focus the window of your "
f"choice.\nStarting in:")
try:
wikipedia.set_lang(selectedlang)
wikipage = wikipedia.random(1)
wikiload = wikipedia.page(wikipage).content
page = split_into_sentences(wikiload)
countdown(5)
print("\r", end='')
print(f"Started!\nSpamming {wikipedia.page(wikipage).title}\n",
end='',
flush=True)
float(timer)
for word in page:
pyautogui.typewrite(word)
pyautogui.press('enter')
time.sleep(float(timer))
print("\r", end='')
print("Done!", end='', flush=True)
except wikipedia.DisambiguationError as e:
s = random.choice(e.options)
p = wikipedia.pages(s)
print(e.options)
except wikipedia.exceptions.PageError:
print("Page not found. Try again with different query.")
try:
wpg = wikipedia.page(
"virat kohli"
) # Wiki page with title = "title" or the pageid = numpageid
print(wpg.content)
print(wpg.categories)
print(wpg.images)
print(wpg.links)
print(wpg.references)
print(wpg.sections)
print(wpg.summary)
except wikipedia.exceptions.DisambiguationError as e:
print(e.options)
except wikipedia.exceptions.PageError:
print("Page not found. Try again with different query.")
print(
wikipedia.languages()
) # List all the currently supported language prefixes (usually ISO language code).
# wikipedia.set_lang(prefix) # set language, but query must be made in the same lang
# requests rate limits
# wikipedia.set_rate_limiting(rate_limit, min_wait=datetime.timedelta(0, 0, 50000))
except Exception as e:
print(str(e))
import wikipedia
# 取り込む記事のディレクトリとタイトル
dirPass = '******'
print('English' in wikipedia.languages())
titles = wikipedia.random(pages=10)
print(titles)
'''
# Wikipediaのテキストデータを取り込む
texts = [wikipedia.page(t, auto_suggest=False).content for t in titles]
for (title, text) in zip(titles, texts):
fName = dirPass + '/' + title.replace(' ', '_').lower() + '.txt'
with open(fName, 'w') as f:
f.write(text)
'''
def busca_idioma(i):
while not i in wikipedia.languages():
i = input("Input no válido: ")
return i
import wikipedia
print(wikipedia.search("Bill"))
print(wikipedia.suggest("Bill cliton"))
#print(wikipedia.summary("Ubuntu"))
# print(wikipedia.summary("key"))
# print(wikipedia.summary("Key (cryptography)"))
print(wikipedia.page("Ubuntu"))
print(wikipedia.page("Python").content)
print(wikipedia.page("Python").url)
print(wikipedia.page("Python").references)
print(wikipedia.page("Python").title)
print(wikipedia.page("Python").categories)
print(wikipedia.page("Ubuntu").links)
print(wikipedia.geosearch(37.787, -122.4))
print(wikipedia.page(37.787, -122.4))
wikipedia.set_lang("de")
print(wikipedia.summary("ubuntu", sentences=2))
print(wikipedia.languages())
print(wikipedia.page("ubuntu").images[0])
print(wikipedia.page("Ubuntu").html())
def checklang(language):
if (arr[-1] in wikipedia.languages()):
return 1
else:
return 0
def main(argv):
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="fetch snippets of language-specific text from random pages "
"of one or many wikipedias",
)
parser.add_argument(
"--langs",
type=str,
nargs="+",
required=False,
help="one or more languages for which to fetch wiki snippets "
"as ISO 639-1 language codes",
)
parser.add_argument(
"--langs_file",
type=str,
required=False,
help="path to text file on disk containing languages for which to fetch "
"wiki snippets as ISO 639-1 language codes, one per line",
)
parser.add_argument(
"--skip_langs",
type=str,
nargs="+",
required=False,
default=[],
help="one or more languages for which to *skip* fetching wiki snippets "
"as ISO 639-1 language codes, as a convenience",
)
parser.add_argument(
"--outdir",
type=str,
required=False,
help="path to directory on disk to which wiki snippets will be saved",
)
parser.add_argument(
"--n_snippets",
"-n",
type=int,
default=25,
help="number of text snippets to save per language",
)
parser.add_argument(
"--timeout",
type=int,
default=3600,
help="maximum number of seconds to spend fetching snippets, per language",
)
parser.add_argument(
"--mode",
type=str,
choices=["skip", "append", "overwrite"],
default="skip",
help="",
)
parser.add_argument(
"--featured",
action="store_true",
default=False,
help="if set, will attempt to get 'featured articles' for each language "
"before falling back to random pages",
)
parser.add_argument(
"--good",
action="store_true",
default=False,
help="if set, will attempt to get 'good articles' for each language "
"before falling back to random pages",
)
args = parser.parse_args(argv)
if not bool(args.langs) ^ bool(args.langs_file):
raise ValueError("either `langs` or `langs_file` must be specified")
if args.langs_file:
with io.open(args.langs_file, mode="rt", encoding="utf-8") as f:
langs = [line.strip() for line in f]
else:
langs = args.langs
outdir = os.path.realpath(os.path.expanduser(args.outdir)) if args.outdir else None
featured = (
get_all_lang_links("Category:Featured_articles", "en") if args.featured else None
)
good = get_all_lang_links("Category:Good_articles", "en") if args.good else None
wikipedia.set_rate_limiting(True, min_wait=datetime.timedelta(milliseconds=10))
wiki_langs = wikipedia.languages()
for i, lang in enumerate(langs):
if lang not in wiki_langs:
raise ValueError(
"lang='{}' is invalid; available langs are\n{}".format(
lang, sorted(wiki_langs.keys())
)
)
wikilang = wiki_langs[lang]
if lang in args.skip_langs:
logging.info(
"skipping lang %s '%s' (%s/%s) ...", wikilang, lang, i + 1, len(langs),
)
continue
n_snippets = args.n_snippets
mode = "wt"
if outdir:
fname = os.path.join(outdir, lang + ".txt")
if os.path.isfile(fname):
if args.mode == "skip":
logging.info(
"snippets for lang %s '%s' (%s/%s) already fetched, skipping ...",
wikilang,
lang,
i + 1,
len(langs),
)
continue
else:
with io.open(fname, mode="rt", encoding="utf-8") as f:
n_snippets_existing = sum(1 for _ in f)
if args.mode == "append":
mode = "at"
n_snippets = max(n_snippets - n_snippets_existing, 0)
if n_snippets == 0:
logging.info(
"snippets for lang %s '%s' (%s/%s) already fetched, skipping ...",
wikilang,
lang,
i + 1,
len(langs),
)
continue
logging.info(
"fetching snippets for lang %s '%s' (%s/%s) "
"to %s %s existing snippets ...",
wikilang,
lang,
i + 1,
len(langs),
args.mode,
n_snippets_existing,
)
else:
logging.info(
"fetching snippets for lang %s '%s' (%s/%s) ...",
wiki_langs[lang],
lang,
i + 1,
len(langs),
)
else:
logging.info(
"fetching snippets for lang %s '%s' (%s/%s) ...",
wiki_langs[lang],
lang,
i + 1,
len(langs),
)
snippets = get_snippets(lang, n_snippets, featured, good, args.timeout)
if outdir:
with io.open(fname, mode=mode, encoding="utf-8") as f:
for snippet in snippets:
f.write(snippet + "\n")
logging.info("saved %s %s snippets to %s", len(snippets), lang, fname)
else:
logging.info(
"fetched %s %s snippets but did not save to disk:\n%s\n...",
len(snippets),
lang,
snippets[:3],
)
def lang_select(self,lng):
"set language for the request"
print "Language set to:",wikipedia.languages()[lng]
wikipedia.set_lang(lng)
def is_right_lang(lang):
return lang in wikipedia.languages()
