def haripuisi_html(url):
page = down.download(url)
page = down.del_html(page)
with open('page.html', 'w', encoding='utf-8') as f:
f.write(page)
soup = BeautifulSoup(page, 'lxml')
return soup
def take_word_page(word):
html = down.download('https://kbbi.web.id/' + word.lower())
if html is None:
print('Сорян, слово не найдено! Печалька :(')
else:
with open(r'html_changing.txt', 'w', encoding='utf-8') as f:
f.write(down.del_html(html.replace('·', '')))
return down.del_html(html.replace('·', ''))
def abdul_hadi_html():
page = down.download(
'http://www.jendelasastra.com/dapur-sastra/dapur-jendela-sastra/lain-lain/puisi-puisi-abdul-hadi-wm'
)
page1 = down.del_html(page)
with open('abdul_h.html', 'w', encoding='utf-8') as f:
f.write(page1)
return page1
def take_word_page(word):
html = down.download('https://kbbi.web.id/' + word.lower())
if html is None:
print('Прости, Настюш, но у тебя опять упал инет:(')
else:
with open(r'html_changing.txt', 'w', encoding='utf-8') as f:
f.write(down.del_html(html.replace('·', '')))
return down.del_html(html.replace('·', ''))
def haripuisi_insert_url(url):
page_poem = down.download(url)
page_poem = down.del_html(page_poem)
soup = BeautifulSoup(page_poem, 'lxml')
filename = re.sub('[~#&%*{}:?"|+/<>]', '', str(soup.title.string)).strip() + '.txt'
with open('haripuisi\\' + filename, 'a', encoding='utf-8') as f:
f.write('\n' + url)
print(filename + ' - done')
def haripuisi_download_poems(url):
page_poem = down.download(url)
page_poem = down.del_html(page_poem)
soup = BeautifulSoup(page_poem, 'lxml')
filename = re.sub('[~#&%*{}:?"|+/<>]', '', str(soup.title.string)).strip() + '.txt'
get_poem = soup.find('div', {'class': 'entry-content'}).contents
div_tag = re.compile('<div.*?>.*?</div>', re.DOTALL)
poem = []
for i in get_poem:
poem_with_tags = re.sub(div_tag, '', str(i))
poem1 = re.sub('<.*?>', '\n', poem_with_tags)
poem.append(poem1)
with open('haripuisi\\' + filename, 'w', encoding='utf-8') as f:
f.write('\n'.join(poem))
print(filename + ' - done')
def gusmus_crouler():
poems = []
for n in range(1, 12):
page = down.download('http://gusmus.net/puisi/?N={}'.format(str(n)))
page1 = down.del_html(page)
soup = BeautifulSoup(page1, 'lxml')
container = soup.find_all('div', {'class': 'col-xs-12 col-sm-10 blog-content'})
for i in container:
regex = re.compile('<.*?>', re.DOTALL)
text = re.sub(regex, '\n', str(i))
text_ready = re.sub('\n{2,}', '\n', text)
text_ready = re.sub('\xa0', ' ', text_ready)
poems.append(text_ready.strip())
file_name = 'Mustofa Bisri\\A. Mustofa Bisri - ' + text_ready.strip().split('\n')[0].capitalize() + '.txt'
print(file_name)
with open(file_name, 'w', encoding='utf-8') as f:
f.write('http://gusmus.net/puisi/?N={}'.format(str(n)))
f.write(text_ready)
print(poems)