def search(self): """ Takes value from text fields and uses the wiki algorithm""" self.text.delete(0.0, END) # Assigns start to random if empty x = self.start.get() y = self.end.get() if x == '': while True: try: x = wikipedia.random(1) self.text.insert(0.0, 'Random start is %s.\n' % x) break except UnicodeEncodeError: pass # Assigns end to random if empty if y == '': while True: try: y = wikipedia.random(1) self.text.insert(0.0, 'Random end is %s.\n' % y) break except UnicodeEncodeError: pass self.text.insert(0.0, 'Start is %s.\nTarget is %s.\n' % (x,y))
def get_random_articles_v2():
"""Retrieves random articles until the user types 'stop' """
ans = input('Press enter to continue or stop to stop: ')
while ans != 'stop':
try:
print(wikipedia.summary(wikipedia.random()))
print()
ans = input('Press enter to continue or stop to stop: ')
except wikipedia.exceptions.DisambiguationError:
print(wikipedia.summary(wikipedia.random()))
print()
ans = input('Press enter to continue or stop to stop: ')
def getPage():
rpage = wikipedia.page(wikipedia.random(1))
while len(rpage.content) <= minlength:
try:
#TODO: Exception for lists
rpage = wikipedia.page(wikipedia.random(1))
except wikipedia.exceptions.DisambiguationError as e:
print 'ERROR'
rpage = wikipedia.page(e.options[0])
else:
print 'MISS'
rpage = wikipedia.page(wikipedia.random(1))
return rpage
def get_random_page():
# https://wikipedia.readthedocs.org/en/latest/quickstart.html
random_title = wikipedia.random(pages=1)
random_page = None
while not random_page:
try:
random_page = wikipedia.page(title=random_title)
except wikipedia.PageError:
random_title = wikipedia.random(pages=1)
random_page = None
except wikipedia.DisambiguationError as e:
random_title = random.choice(e.options)
random_page = None
return random_page
def wikipedia_random(self, n):
print "Downloading pages from Wikipedia. This may take a moment..."
f = open(self.inf, "w")
pages = []
# get a list of random wikipedia pages.
# wikipedia.random can only get 10 at a time, so call it so many times
for x in range(n/10):
pages += (wikipedia.random(10))
if n%10 > 0:
pages += (wikipedia.random(n%10))
log.info("Found {} random wikipedia pages".format(len(pages)))
# get the summary info from all the pages.
# this is a lot of pages, so can take some time
for page in pages:
info = None
try:
log.debug("Getting page "+page)
info = wikipedia.page(page)
# if the request threw a disambiguation error, try to get the first suggestion
# if that files, just give up on that request. we didn't want it that much anyway
except wikipedia.exceptions.DisambiguationError as e:
try:
log.debug("Getting page "+page)
info = wikipedia.page(e.options[0])
except wikipedia.exceptions.DisambiguationError as e:
continue
except (wikipedia.exceptions.HTTPTimeoutError, wikipedia.exceptions.PageError):
continue
except (wikipedia.exceptions.HTTPTimeoutError, wikipedia.exceptions.PageError):
continue
# save the summary. if it exceeds 127 characters, try to truncate by the first sentence end.
# if that fails, write it anyway, but it will give warning when it generates the config
s = info.summary.encode("ascii", "ignore").replace("\n", " ")
if len(s) < 127:
log.info("Wrote line with no edits")
f.write(s + "\n")
else:
if s[:127].rfind(". ") != -1:
f.write(s[:s[:127].rfind(". ")+1] + "\n")
log.info("Summary too long, but was truncated")
else:
f.write(s + "\n")
log.info("Summary too long and couldn't truncate")
f.close()
def __init__(self):
try:
self.page = wikipedia.page((wikipedia.random(pages=1)))
self.name = self.page.title
self.summary = self.page.summary
except wikipedia.DisambiguationError:
Wiki_page()
def get_random_wiki():
random_wiki = wikipedia.random()
random_wiki_page = wikipedia.page(random_wiki)
summary = wikipedia.summary(random_wiki, sentences=1)
return random_wiki_page.title, random_wiki_page.url, summary
def run(self, articles_number, words_number, result_file):
result = []
most_common_words = load_most_commons_words()
most_common_words = most_common_words[:words_number]
if words_number > len(most_common_words):
raise ValueError("most_common_words database too small: {} > {}".format(
words_number, len(most_common_words)))
bar = progressbar.ProgressBar()
for n in bar(range(articles_number)):
article_words_occurrence = [0] * words_number
while True:
try:
page = wikipedia.page(wikipedia.random(), auto_suggest=True)
break
except Exception:
pass
for word in simplify_article_and_return_words(page.content):
if word in most_common_words:
article_words_occurrence[most_common_words.index(word)] += 1
result.append(article_words_occurrence)
with open(result_file, "w") as f:
f.write("\n".join([",".join(str(number) for number in row) for row in result]))
async def wiki(self, c: Command):
wikipedia.set_lang(self.settings["language"])
sentences = self.settings["sentences"]
query = c.message
# expected response for choosing a topic from `self.searches`
if len(query) == 1 and query.isdigit():
query = self.searches[int(query)]
elif len(query) == 0:
query = wikipedia.random(pages=1)
try:
page = wikipedia.page(query)
summary = wikipedia.summary(query, sentences=sentences)
except wikipedia.exceptions.PageError as err:
await self.send_message("PageError, FIXME")
except wikipedia.exceptions.DisambiguationError as err:
self.searches = err.options[:10]
# iterate over self.searches to create a formated string,
# ie "0) List Index 0\n1) List Index 1" etc
fmtd = "\n".join([str(i)+") "+m for i,m in enumerate(self.searches)])
await self.send_message("Select one with \"wiki #\"\n{}".format(fmtd), clean=False)
else:
url = page.url
# wikipedia lib reformats headings? yuck.
summary = re.sub("==.+==", " ", summary)
summary = re.sub("\n", "", summary)
# TODO maybe pull this limit from the settings
await self.send_message("{}\n{}".format(url,summary), clean=False, limit=1)
def random_calling():
quesion = wikipedia.random(1)
print(quesion, len(str(quesion).split()))
if len(str(quesion).split()) == 1:
return str(quesion)
else:
return random_calling()
def getArt():
randArt = wikipedia.random(pages = 1)
userInput = input("Would you like to read about %s? " %randArt)
if userInput.lower() == "yes" or userInput.lower() == "y":
launchArt(randArt)
if userInput.lower() == "no" or userInput.lower() == "n":
getArt()
def get_wikipedia_random_pages(size_mbytes):
print 'Starting download random pages from wikipedia, writing to file %s' % WIKI_OUTPUT_FILE
output_file = open(WIKI_OUTPUT_FILE, 'a')
curr_progress = 0
curr_size = 0
iters = 0
data_size_iter = 0
size_bytes = MBytesToBytes(size_mbytes)
start = time.time()
while curr_size < size_bytes:
try:
print 'Starting iteration %d ' % iters
itemset = wikipedia.page(wikipedia.random(
pages=1)).content.encode('utf-8').lower().split(" ")
except:
continue
itemset_hashes = [str(hash(word)) for word in itemset]
itemset_line = " ".join(itemset_hashes) + NEWLINE
data_size_iter += len(itemset_line)
curr_size += len(itemset_line)
iters += 1
output_file.write(itemset_line)
if curr_size > curr_progress + PROGRESS:
print 'Already written %d bytes' % curr_size
if iters % 10 == 0:
end = time.time()
print 'Current 10 iterations took %d seconds and %s bytes collected' % (
(end - start), data_size_iter)
data_size_iter = 0
start = time.time()
output_file.close()
def randomWiki():
'''
This function gives you a list of n number of random articles
Choose any article.
'''
number=input("No: of Random Pages : ")
lst=wk.random(number)
for i in enumerate(lst):
print(i)
try:
key=input("Enter the number : ")
assert key>=0 and key<number
except AssertionError:
key=input("Please enter corresponding article number : ")
page=wk.page(lst[key])
url=page.url
#originalTitle=page.original_title
pageId=page.pageid
#references=page.references
title=page.title
#soup=BeautifulSoup(page.content,'lxml')
pageLength=input('''Wiki Page Type : 1.Full 2.Summary : ''')
if pageLength==1:
soup=fullPage(page)
print(soup)
else:
print(title)
print("Page Id = ",pageId)
print(page.summary)
print("Page Link = ",url)
#print "References : ",references
pass
def get_decoys(self, target):
decoy1_search = []
import wikipedia
while len(decoy1_search) < target:
try:
decoy1 = wikipedia.page(wikipedia.random())
decoy1_query = wikipedia.search(decoy1)
for i in range(len(decoy1_query)):
if len(decoy1_search) >= target:
break
else:
try:
member0 = wikipedia.page(decoy1_query[i])
member0_list = member0.references
for j in range(len(member0_list)):
decoy1_search += [['00', member0_list[j]]]
if len(decoy1_search) >= target:
break
except:
continue
except:
continue
return decoy1_search
def getRandArticle():
# getting directory for easy use
myPath = os.path.expanduser("~/documents/contexter/")
# how many articles to get
for x in xrange(0, 1):
# Get an article, if DisambiguationError, then try again
try:
article = wikipedia.random()
except wikipedia.exceptions.DisambiguationError:
print "Disambiguation, retrying..."
article = wikipedia.random()
except wikipedia.exceptions.PageError:
print "PageError, retrying..."
article = wikipedia.random()
pageObj = wikipedia.page(article)
text = pageObj.content
pageUrl = pageObj.url
# Writing the text and to the created file, encoded utf8
f = open(article + ".txt", "w")
f.write(text.encode('utf-8'))
f.close()
# Getting all lines
f = open(article + ".txt", "r")
tempText = f.readlines()
f.close()
# Decoding all lines for cleanup of file
for i, v in enumerate(tempText):
tempText[i] = tempText[i].decode('utf-8')
# Clean up the file, the file has '==' characters denoting sections
f = open(article + ".txt", "w")
for line in tempText:
if ('==' not in line):
f.write(line.encode('utf-8'))
f.close()
# move file into raw text folder
shutil.move(myPath + "scripts/" + article + ".txt", myPath + "/raw text/" + article + ".txt")
articleLoc = myPath + "/raw text/" + article + ".txt"
return [articleLoc, pageUrl]
def makePage():
# get new random page
global page
text.delete(1.0, END)
try:
page = wikipedia.page((wikipedia.random(pages=1)))
except wikipedia.DisambiguationError:
makePage()
def read_random_from_topic(topic = None):
"""Reads from a topic (or random topic if not specified), and returns
an internal content type that includes a random sentence"""
if not topic:
topic = wikipedia.random()
content = wikipedia.page(topic)
return to_system_format(content)
def summary(article):
summary_list = []
if article is None:
article = wikipedia.random()
if article is not None:
summary = wikipedia.summary(article)
summary_list.append(summary)
return summary_list
def insert_random_loop(self):
i = 1
while True:
ra = wikipedia.random()
article = wikipedia.page(ra)
self.rs.add_document(f'doc{i}', title=article.title, body=article.content)
print(f'>>> Inserted {article.title}')
i += 1
def get_wp_pages():
#Returns a list of Wikipedia page titles, to be used as concepts
pagenames = []
for item in wikipedia.random(pages=8):
if len(item) < 18:
pagenames.append(item)
return pagenames
def get_title( progress_count ):
"""Obtain title of a random wikipedia article, checking it's not a disambiguation."""
# Print progress
sys.stdout.write( "%d " %progress_count )
sys.stdout.flush()
# Get title, try to load page. Pick another if there's a disambiguation error.
while True:
try:
title = wikipedia.random()
wikipedia.page( title )
break
except ( wikipedia.exceptions.DisambiguationError, wikipedia.exceptions.PageError ):
title = wikipedia.random()
return title
def runArticleDownloader():
for i in range(1, 2501):
query = wikipedia.random(1)
try:
article = wikipedia.page(query)
except:
continue
save_to_file(article.url, article.summary)
def fact():
pageTitle = wikipedia.random();
page = wikipedia.summary(pageTitle, sentences=1);
if ("is" in page or "was" in page) and page[0] != '<':
page = re.sub("[\(\[].*?[\)\]]", "", page)
return page
else:
return fact()
def GetArticle(): """ Generates an article """ try: return wikipedia.page(wikipedia.random()) except: # an error ocurred, probably gone to a disambiguation page, try again return GetArticle()
def __init__(self):
self.page = None
while self.page is None:
try:
title = wikipedia.random()
self.page = wikipedia.page(title=title)
except:
pass
def index(request):
wikipedia.set_lang("fr")
titreArticle = []
for i in range(1, 100):
titreArticle.append(wikipedia.random(pages=1))
context = {"titre": titreArticle}
return render(request, 'home.html', context)
def fact():
pageTitle = wikipedia.random()
page = wikipedia.summary(pageTitle, sentences=1)
if ("is" in page or "was" in page) and page[0] != '<':
page = re.sub("[\(\[].*?[\)\]]", "", page)
return page
else:
return fact()
def find_pages(lang_wiki='de',
to_extract=1000,
max_time_s=4 * 60 * 60,
verbose=False):
"""
Extract paragraphs from random wikipedia pages of a given language.
Parameters
----------
lang_wiki : str, optional (default: de)
to_extract : int, optional (default: 1000)
Number of paragraphs to be extracted
max_time_s : int, optional (default: 4h)
Maximum time in seconds to run the paragraph extraction.
verbose : boolen, optional (default: False)
Returns
-------
tuple : extracted_paragraphs, list of source pages
"""
wikipedia.set_lang(lang_wiki)
extracted_paragraphs = []
used_pages = set()
queried = []
bar = progressbar.ProgressBar(redirect_stdout=True, max_value=to_extract)
t0 = time.time()
while (len(extracted_paragraphs) < to_extract
and (time.time() - t0) < max_time_s):
random_pages = wikipedia.random(pages=10)
for random_page in random_pages:
if '/' in random_page:
# see https://to.wikipedia.org/wiki/Tuʻi_Tonga_Fefine/en
continue
parse_page(random_page, extracted_paragraphs, queried, used_pages,
bar, verbose, to_extract)
# print("Start extracting pages")
if False and len(extracted_paragraphs) < to_extract:
apcontinue = ''
max_reached = False
while not max_reached and len(extracted_paragraphs) < to_extract:
out = get_all_page_titles(lang_wiki,
apcontinue=apcontinue,
max_pages=10)
page_titles_queue = out['page_titles']
max_reached = out['max_reached']
apcontinue = out['apcontinue']
random.shuffle(page_titles_queue)
print("Loaded {} pages".format(len(page_titles_queue)))
while (len(extracted_paragraphs) < to_extract
and len(page_titles_queue) > 0):
print(len(page_titles_queue))
page_title, revision_id = page_titles_queue.pop()
parse_page(page_title, extracted_paragraphs, queried,
used_pages, bar, verbose)
bar.update(to_extract)
bar.finish()
return extracted_paragraphs, list(used_pages)
def get_random_articles_v1(number_of_articles_wanted):
"""Given the wanted number of articles returned, get random wikipedia articles"""
if number_of_articles_wanted == 1:
print(wikipedia.summary(wikipedia.random()))
else:
list_of_articles = wikipedia.random(number_of_articles_wanted)
try:
for a in list_of_articles:
article = a[:]
if ('disambiguation' in wikipedia.page(a).title) or ('it may refer to' in wikipedia.page(a).title):
list_of_articles.remove(a)
list_of_articles.append(wikipedia.random())
print(list_of_articles.index(a)+1," - "+wikipedia.summary(a))
print()
except wikipedia.exceptions.DisambiguationError:
list_of_articles.remove(article)
list_of_articles.append(wikipedia.random(article))
def random_page():
wikipedia.set_lang("fy")
random = wikipedia.random(1)
try:
result = wikipedia.page(random).summary
except wikipedia.exceptions.DisambiguationError as e:
result = random_page()
return result
def random_wikipedia_article():
title = wikipedia.random(pages=1)
try:
return wikipedia.page(title).content
except wikipedia.exceptions.DisambiguationError:
# wikipedia.exceptions.DisambiguationError as e:
# sometimes, the line wikipedia.page(e.options[0]).content raises again a DisambiguationError exception,
# which is unfortunate (see for example the wikipedia page 'Shadi')
return random_wikipedia_article()
def wiki():
page = wikipedia.random(1)
var = "Do you wanna read about "+page+" ?"
label = tk.Label(root, text=var, fg='red', font = ('calibri',10))
label.place(relx=0.4,rely=0.3)
yes = tk.Button(root, text='Yes', command = lambda:yes1(page) ,font = ('calibri',10))
yes.place(relx=0.4,rely=0.5, relheight=0.2, relwidth=0.2)
no = tk.Button(root, text='No', command = wiki ,font = ('calibri',10))
no.place(relx=0.4,rely=0.7, relheight=0.2, relwidth=0.2)
def random(message):
# noinspection PyBroadException
try:
random_title = str(wikipedia.random(pages=1))
random_page = wikipedia.page(random_title)
random_result = str(random_page.url)
bot.send_message(chat_id=message.chat.id, text=random_result, reply_markup=main_keyboard())
except Exception:
bot.send_message(chat_id=message.chat.id, text=error, reply_markup=main_keyboard())
def random_page():
random = wikipedia.random(1)
try:
result = wikipedia.page(random)
except wikipedia.exceptions.DisambiguationError as e:
result = random_page()
print('\033[1m' + result.title + '\033[0m \n')
print(result.summary + '\n')
print(result.url)
def on_click_random(self, num):
random_text = wikipedia.random()
while (len(random_text) >= 17):
random_text = wikipedia.random()
if num is 1:
self.ids.search_one.text = random_text
self.ids.compare_button.disabled = True
self.ids.detect_one.background_normal = 'red_bar2.png'
else:
self.ids.search_two.text = random_text
self.ids.compare_button.disabled = True
self.ids.detect_two.background_normal = 'red_bar2.png'
pass
def test_random_pages(self):
print("------ random pages test ------------")
pages = wikipedia.random(2)
print(pages)
article1 = Article(pages[0], repo=DataDict())
article2 = Article(pages[1], op=op_backlinks, repo=DataDict())
run_test(article1, article2)
print('=========================================')
def handle_random_intent(self, message):
""" Get a random wiki page.
Uses the Special:Random page of wikipedia
"""
# Talk to the user, as this can take a little time...
search = wiki.random(pages=1)
self.speak_dialog("searching", {"query": search})
self._lookup(search)
def main(out: str):
outpath = pathlib.Path(out)
random_pages = map(lambda title: wikipedia.page(title),
wikipedia.random(10))
for page in random_pages:
filename = outpath.joinpath(page.title).with_suffix(".txt")
with filename.open("w") as f:
f.write(page.content)
def test_random_pages(self):
print("------ random pages test ------------")
pages = wikipedia.random(2)
print(pages)
article1 = Article(pages[0], repo=DataDict())
article2 = Article(pages[1], op=op_backlinks, repo=DataDict())
run_test(article1, article2)
print('=========================================')
def newAnswers():
alternates = wikipedia.random(ALTERNATE_OPTIONS)
choices = []
choices.extend(alternates)
choices.append(correctAnswer)
shuffle(choices)
prefixes = [i for i in range(len(choices))]
answers = dict(zip(prefixes, choices))
return answers
def get_random_wiki():
page_name = wikipedia.random(1)
try:
page_link = wikipedia.page(page_name).url
return page_link, page_name
except wikipedia.exceptions.DisambiguationError:
return None, None
except wikipedia.exceptions.PageError:
return None, None
async def get_random_wikipedia_page(self, ctx):
"""wikipediaからランダムな記事を一つ取得する"""
await ctx.send("妹「wikipediaからランダムな記事を取ってくるね！」")
await ctx.send("妹は中空に手を翳し、何かを掴むような動作をしている。")
# 日本語wikipediaからランダムな単語を一つ決めてページを取得する
self.wikipedia_page = wikipedia.page(wikipedia.random())
await ctx.send("妹「ランダムな記事を取ってきたよ！」")
def index_wikipedia(num_pages):
for _ in range(0, num_pages):
p = wikipedia.random()
try:
wiki_page = wikipedia.page(p)
Page.objects.update_or_create(
title=wiki_page.title, defaults={"content": wiki_page.content}
)
except Exception:
logger.exception("Failed to index %s", p)
def gethering_pages(no,pages_no):
if no == 1:
print("Fatching 1st 20 pages.")
else:
print("Fatching next 20 pages.")
page_names = [wikipedia.random(1) for i in range(pages_no)]
pages = page_names
return pages
def wikirandom(sents, boole, client, message, lang="it"):
wikipedia.set_lang(lang)
wikipedia.set_rate_limiting(rate_limit=True)
random = wikipedia.random()
result = wikipedia.summary(random, sentences=sents)
if boole:
return result
else:
result += "\n" + create_link(random, lang)
return utils.get_config.sendMessage(client, message, result)
def random_page():
# Fetches a random page from wikipedia
try:
page = wikipedia.page(wikipedia.random())
print(page.links)
show_links(page)
# Deals with wiki disambiguation error
except wikipedia.exceptions.DisambiguationError:
random_page()
def wiki():
global page
random_article = wikipedia.random()
page = wikipedia.page(random_article)
contents = page.summary
sentences = contents.split(". ")
os.system("clear")
return sentences
def random():
try:
query = wikipedia.random(pages=1)
input = wikipedia.WikipediaPage(title=query).summary
title = wikipedia.WikipediaPage(title=query).title
image = wikipedia.WikipediaPage(title=query).images[0]
client = Algorithmia.client('Simple simR+{}'.format(api_key))
algo = client.algo('nlp/Summarizer/0.1.2')
contents ={
'image': image,
'title': title,
'summary': algo.pipe(input),
'link': 'https://en.wikipedia.org/wiki/{}'.format(wikipedia.random(pages=1))
}
except:
return json.dumps({
'msg': "Sorry, we couldn't find a Wikipedia article matching your search."
})
return json.dumps(contents)
def do_til(self, arg):
if check_core('DISCIPLINE') is not True:
req = urllib2.Request("http://hipsteripsum.me/?paras=1&type=hipster-centric", headers={'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1664.3 Safari/537.36', "Accept" : "text/html"})
contents = urllib2.urlopen(req).read()
soup = BeautifulSoup(contents, "html5lib")
for div in soup.find_all(id='content'):
text = div.contents[1].string
elif check_core("CURIOSITY") is True and check_core('EMPATHY') is True:
wikipedia.set_lang("en")
print "english"
text = wikipedia.summary(wikipedia.random(pages=1))
elif check_core("CURIOSITY") is not True:
wikipedia.set_lang("simple")
print "simple"
text = wikipedia.summary(wikipedia.random(pages=1))
elif check_core("CURIOSITY") is True and check_core('EMPATHY') is not True:
req = urllib2.Request("http://www.elsewhere.org/pomo/", headers={"Accept" : "text/html"})
contents = urllib2.urlopen(req).read()
soup = BeautifulSoup(contents, "html5lib")
h3counter = 0
text = ''
for div in soup.find_all('div', class_='storycontent'):
for element in div.contents:
if element.name == 'h1':
text = text + element.string + '\n'
elif element.name == 'h3' and h3counter < 1:
text = text + element.string + '\n'
h3counter = h3counter + 1
elif element.name == 'h3' and h3counter == 1:
break
elif element.name == 'p' and element.string is not None:
text = text + element.string + '\n'
question = "Is that interesting " + dev_names[random.randint(0, len(dev_names)-1)] + "?"
say(text, agnes_core.voice)
if check_core("CURIOSITY") is not True:
say(question, agnes_core.voice)
def get_random_page(): """Return a random wikipedia page as a wikipedia object. """ ambig_error = True while ambig_error: ambig_error = False try: page = wikipedia.page(wikipedia.random()) except wikipedia.exceptions.DisambiguationError: ambig_error = True return page
def random(self, c, e, args):
while True:
try:
p = wikipedia.page(wikipedia.random())
if p:
c.privmsg(get_target(c, e),
'\x02{}\x0f - {} [ {} ]'.format(p.title, smart_truncate(p.summary.replace('\n', ' ')),
p.url))
break
except DisambiguationError:
pass
def get_random_page(nsent):
"""
Get sentences from random page (up to nsent sentences)
"""
page = wiki.page(wiki.random())
sentences = split_content(page.content)
sentences = filter_noise(sentences)
ct = len(sentences)
takenct = min(nsent, ct)
takensent = sentences[:takenct]
return (takensent, takenct)
def main(begin, end):
# TODO: FIX DISAMBIGUATION ERRORS ###########################################
try:
start = wikipedia.page(begin) if begin != "" else wikipedia.page(wikipedia.random())
except wikipedia.exceptions.PageError:
return ("\nSorry the start page %s doesn't exist" %begin)
try:
dest = wikipedia.page(end) if end != "" else wikipedia.page(wikipedia.random())
except wikipedia.exceptions.PageError:
return ("\nSorry the ending page %s doesn't exist" %end)
#############################################################################
previousList = []
listOfConnections = []
currentList = getLinks(start.title, masterList)
result = 1;
for y in range(len(currentList)):
associateTo(currentList[y],start.title)
if(findLink(currentList, dest) >= 0 ):
listOfConnections = acquireAllAssociations(dest.title,
result, listOfConnections)
else:
previousList = currentList
for i in previousList:
if i not in masterList:
masterList.append(i)
result = layerSearch(previousList, result, dest)
listOfConnections = acquireAllAssociations(dest.title,
result, listOfConnections)
return list(reversed([dest.title] + listOfConnections))
def readRandom():
randomArticles = wikipedia.random(pages=3)
try:
for topic in randomArticles: # string case
crawlAndLearn(topic)
print('Words:' + str(len(words)))
print('POS:' + str(len(partsOfSpeech)))
except AttributeError:
for topic in randomArticles:
crawlAndLearn(topic)
print('Words:' + str(len(words)))
print('POS:' + str(len(partsOfSpeech)))
def handleRandomCommand(self):
"""Gets a random page from Wikipedia and prints the summary paragraph.
"""
returnString = ""
pg = wikipedia.random(1)
try:
returnString = wikipedia.summary(pg)
except wikipedia.exceptions.DisambiguationError:
returnString = self.handleRandomCommand()
return returnString
def wikilookup(choices):
lookup=choices[0]+" "+choices[1]
if debug: print "lookup:",lookup
res=wikipedia.random(pages=5)
for k in res:
print "search",k
p = wikipedia.page(k)
print "title:",p.title
images=p.images
for i in images:
print "image:",i
return []
def simple_giver(num, min_links=5, min_lenth=3000, max_word=1, exclude_titles=exclude_t):
all_pages = []
pages_title = []
while len(all_pages) < num_of_pages:
try:
temp_title = wp.random(pages=1)
temp_content = wp.WikipediaPage(temp_title).content
pages_title.append(temp_title)
all_pages.append(temp_content)
print("page loaded... ", end = " ")
except (wp.exceptions.WikipediaException, KeyError, ValueError):
pass
return(all_pages, pages_title)
def crawl(self):
pagelist=[]
for document in wikipedia.random(self.crawlCount):
try:
doc = wikipedia.page(document)
#create document
page = WikiPage(doc.title,doc.content)
print("page title : %s \n" % page.getTitle())
pagelist.append(page)
except Exception, e:
self.error_file.write('Search failed: {%s} { %s } \n' % (document, e))
print 'Search failed: %s' % e
def loadRandWikiPage(self): """Grabs a random wiki page for start and end of course. Returns tuple: links first position, title second""" try: Random1 = W.random() self.randomPage = W.page(Random1) #If first random page throws ambiguity error, try again except: self.loadRandWikiPage() if self.randomPage.title: return self.randomPage.links, self.randomPage.title else: print "Not valid"
def run_script():
if opts.random:
page = wiki.page(str(wiki.random()))
message = colored('Random Wikipedia Page', 'yellow')
elif not isinstance(opts.search, type(None)):
results = wiki.search(opts.search)
page = show_list(results)
message = colored(str(page.title) + ' Wikipedia Page', 'yellow')
print message
print ''
print_page(page)
