Python wikipedia.page方法代码示例

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def search_wiki(keywords, number_of_search, wiki_pages):
    suggestion = False

    for word in range(0, len(keywords) - 1):
        # print(keywords[word], ">>")
        result_set = wikipedia.search(keywords[word], number_of_search, suggestion)
        for term in result_set:

            try:
                page = wikipedia.page(term, preload=False)
                page_title = page.title
                # page_summary = page.summary
                page_content = page.content
                wiki_pages[page_title] = page_content

            except wikipedia.exceptions.DisambiguationError as error:
                pass
            except wikipedia.exceptions.PageError as error:
                pass
                # print(error.options)

            # print(page_title, len(page_content), type(page_content))

    return wiki_pages 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def get_articles(language, no_words, max_no_articles, search, **kwargs):
    """ Retrieve articles from Wikipedia """
    wikipedia.set_rate_limiting(True) # be polite
    wikipedia.set_lang(language)

    if search is not None:
        titles = wikipedia.search(search, results = max_no_articles)
    else:
        titles = wikipedia.random(pages = max_no_articles)

    articles = []
    current_no_words = 0
    for title in titles:
        print("INFO: loading {}".format(title))
        page = wikipedia.page(title=title)
        content = page.content
        article_no_words = len(content.split())
        current_no_words += article_no_words
        print("INFO: article contains {} words".format(article_no_words))
        articles.append((title, content))
        if current_no_words >= no_words:
            break

    return articles 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def wiki(bot, event, *args):
    """lookup a term on Wikipedia"""

    term = " ".join(args)
    if not term:
        return

    try:
        page = wikipedia.page(term, auto_suggest=False)

        summary = page.summary.strip()
        summary = summary.replace('\r\n', '\n').replace('\r', '\n')
        summary = re.sub('\n+', "\n", summary).replace('\n', '<br /><br />')
        source = _('<i>source: <a href="{}">{}</a></i>').format(page.url, page.url)

        html_text = '<b>"{}"</b><br /><br />{}<br /><br />{}'.format(term, summary, source)
    except wikipedia.exceptions.PageError:
        html_text = _("<i>no entry found for {}</i>").format(term)
    except wikipedia.exceptions.DisambiguationError as e:
        exception_text = str(e).strip().replace("\n", "<br />")
        html_text = "<i>{}</i>".format(exception_text)

    yield from bot.coro_send_message(event.conv, html_text) 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def wiki(bot, update, args):
	try:
		topic = ""
		for arg in args:
			topic += arg + " "
		summary = wikipedia.summary(topic, sentences = 30)
		page = wikipedia.page(topic)
		extra = "\nFor more details visit " + page.url
		summary += extra
		bot.sendChatAction(chat_id = update.message.chat_id, action = ChatAction.TYPING)
		bot.sendMessage(chat_id = update.message.chat_id, parse_mode=ParseMode.HTML, text = summary)

	except wikipedia.exceptions.DisambiguationError as e:
		error = "Please be more specific with your search query as there are a couple of other options meaning the same."
		for options in e.options:
			error += options.decode("utf-8","ignore")+'\n'
		bot.sendChatAction(chat_id = update.message.chat_id, action = ChatAction.TYPING)
		bot.sendMessage(chat_id = update.message.chat_id, text = error)

	except wikipedia.exceptions.PageError:
		error = "No messages could be found with the topic you entered!"
		bot.sendChatAction(chat_id = update.message.chat_id, action = ChatAction.TYPING)
		bot.sendMessage(chat_id = update.message.chat_id, text = error) 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def cli(google,wiki):
	browser = mechanize.Browser()
	browser.set_handle_robots(False)	#Allows everything to be written
	cookies = mechanize.CookieJar()
	browser.set_cookiejar(cookies)
	browser.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.517.41 Safari/534.7')]
	browser.set_handle_refresh(False)	#Sometimes hangs without this
	if(google):
		query = raw_input("Enter the topic you want to search about: ")
		for link in search(query, tld="co.in", num=10, stop=1, pause=2):
			print link
	if(wiki):
		wiki_topic = raw_input('Enter the topic you want to read about: ')
		result = wikipedia.page(title=wiki_topic,auto_suggest=True,redirect=True, preload=False)
		wiki_content = result.content
		print wiki_content 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def wikipedia(self, ctx, *text):
        """Wikipedia search."""     

        if text == ():
            await send_cmd_help(ctx)
            return
        else:            
            s = "_";
            search = ""
            search = s.join(text)
            user = ctx.message.author
            wikiLang = 'en'# Define the Wikipedia language / Most of these are supported » https://nl.wikipedia.org/wiki/ISO_3166-1
            ws = None
            wikipedia.set_lang(wikiLang)# Set the Wikipedia language.
            try:
                ws = wikipedia.page(search)
                wikiUrl = (ws.url.encode('ascii', 'xmlcharrefreplace'))
                await self.bot.say(wikiUrl.decode("utf8"))
            except:
                await self.bot.say( 'Sorry {}, no wiki hit, try to rephrase'.format(user)) 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def translate(to_translate, to_language="auto", language="auto"):
    bahasa_awal = "auto"
    bahasa_tujuan = to_language
    kata = to_translate
    url = 'https://translate.google.com/m?sl=%s&tl=%s&ie=UTF-8&prev=_m&q=%s' % (bahasa_awal, bahasa_tujuan, kata.replace(" ", "+"))
    agent = {'User-Agent':'Mozilla/5.0'}
    cari_hasil = 'class="t0">'
    request = urllib2.Request(url, headers=agent)
    page = urllib2.urlopen(request).read()
    result = page[page.find(cari_hasil)+len(cari_hasil):]
    result = result.split("<")[0]
    return result 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def download_page(url):
    version = (3,0)
    cur_version = sys.version_info
    if cur_version >= version:     #If the Current Version of Python is 3.0 or above
        import urllib,request    #urllib library for Extracting web pages
        try:
            headers = {}
            headers['User-Agent'] = "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36"
            req = urllib,request.Request(url, headers = headers)
            resp = urllib,request.urlopen(req)
            respData = str(resp.read())
            return respData
        except Exception as e:
            print(str(e))
    else:                        #If the Current Version of Python is 2.x
        import urllib2
        try:
            headers = {}
            headers['User-Agent'] = "Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.27 Safari/537.17"
            req = urllib2.Request(url, headers = headers)
            response = urllib2.urlopen(req)
            page = response.read()
            return page
        except:
            return"Page Not found"

#Finding 'Next Image' from the given raw page 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def _images_get_all_items(page):
    items = []
    while True:
        item, end_content = _images_get_next_item(page)
        if item == "no_links":
            break
        else:
            items.append(item)      #Append all the links in the list named 'Links'
            time.sleep(0.1)        #Timer could be used to slow down the request for image downloads
            page = page[end_content:]
    return items 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def download_pages():
    bonus_questions = BonusQuestionDatabase().all_questions()
    train_answers = set()
    for q in bonus_questions.values():
        train_answers.update(q.pages)
    
    if os.path.isfile(BONUS_ANSWER_PAGES):
        with open(BONUS_ANSWER_PAGES, 'rb') as f:
            try:
                pages = pickle.load(f)
                print('loaded {} pages'.format(len(pages)))
            except EOFError:
                pages = dict()
    else:
        pages = dict()

    train_answers = train_answers - set(pages.keys())

    for answer in tqdm(train_answers):
        if answer in pages:
            continue
        try:
            page = wikipedia.page(answer)
        except (DisambiguationError, PageError, ConnectionError) as e:
            if isinstance(e, DisambiguationError):
                pages[answer] = None
                continue
            if isinstance(e, PageError):
                pages[answer] = None
                continue
            if isinstance(e, ConnectionError):
                break
        try:
            pages[answer] = [page.title, page.content, page.links,
                    page.summary, page.categories, page.url, page.pageid]
        except ConnectionError:
            break

    with open(BONUS_ANSWER_PAGES, 'wb') as f:
        pickle.dump(pages, f) 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def wikipedia_page(message, option, query):
    """
    Wikipediaで検索した結果を返す
    """
    if query == 'help':
        return

    # set language
    lang = 'ja'
    if option:
        _, lang = option.split('-')
    wikipedia.set_lang(lang)

    try:
        # search with query
        results = wikipedia.search(query)
    except:
        botsend(message, '指定された言語 `{}` は存在しません'.format(lang))
        return

    # get first result
    if results:
        page = wikipedia.page(results[0])

        attachments = [{
            'fallback': 'Wikipedia: {}'.format(page.title),
            'pretext': 'Wikipedia: <{}|{}>'.format(page.url, page.title),
            'text': page.summary,
        }]
        botwebapi(message, attachments)
    else:
        botsend(message, '`{}` に該当するページはありません'.format(query)) 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def summary(self, query, sentences=0, chars=0):
        """Returns a plain text summary from the query's page."""
        try:
            return wikipedia.summary(query, sentences, chars)
        except wikipedia.exceptions.PageError:
            return "No page matches, try another item."
        except wikipedia.exceptions.DisambiguationError as error:
            return error.options[:5] 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def content(
            self,
            title=None,
            pageid=None,
            auto_suggest=True,
            redirect=True,
            preload=False):
        """Returns plain text content of query's page, excluding images, tables and other data."""
        try:
            page = wikipedia.page(title)
            return page.content
        except wikipedia.exceptions.PageError:
            return "No page matches, try another item."
        except wikipedia.exceptions.DisambiguationError as error:
            return error.options[:5] 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def searchWikipedia(target):

    try:
        wikipedia.set_lang("es")
        d0 = wikipedia.search(target)

        if d0:
            print()
            print("|----[INFO][WIKIPEDIA][>] ")
            print("     |----[INFO][SEARCH][>] ")
            print("     - Resultados encontrados: ")
            for r in d0:
                print("     - " + r)
        else:
            print("|----[INFO][WIKIPEDIA][>] No aparecen resultados en WIKIPEDIA.")

    except:
        print("[!][WARNING][WIKIPEDIA][>] Error en la API...")

    try:
        d1 = wikipedia.page(target)

        linksWIKI = d1.links
        urlWIKI = d1.url

        if d1:
            print("     |----[INFO][TAGS][>] ")
            for l in linksWIKI:
                print("     - " + l)
            print("|----[FUENTES][WIKIPEDIA][>] ")
            print("     - " + urlWIKI)
            config.wikipediaData_list.append(urlWIKI)
        else:
            print("|----[INFO][WIKIPEDIA][>] No aparecen resultados en WIKIPEDIA.")
    
    except:
        print("[!][WARNING][WIKIPEDIA][>] Error en la API o no aparecen resultados...")

#Funciones para buscar en Youtube 

# 需要导入模块: import wikipedia [as 别名]
# 或者: from wikipedia import page [as 别名]
def get_next(self):
        if self.done:
            return None  # Source exhausted
        while True:
            if self.article_done:
                try:  # Try next title
                    next_title = next(self.title_reader)
                except StopIteration:
                    self.done = True  # Source exhausted
                    return None
                # Get next article
                logger.debug("Next article: {}".format(next_title))
                article = wikipedia.page(next_title).content
                # Split article in sentences
                self.sentences = iter(article.split("."))
                self.article_done = False
            try:  # Try next sentence
                sentence = next(self.sentences)
                logger.debug("Next sentence: {}".format(sentence))
                return sentence
            except StopIteration:
                self.article_done = True


# Splits input line into words and
# outputs records of the form (word,1)