def function_load(self, url):
soup = BeautifulSoup(get_html(url),
'lxml').find('div', class_='b-singlepost-wrapper')
title = soup.find('h1').text
post = soup.find("div", class_="b-singlepost-bodywrapper")
self.load_post(url, title, post)
return title
def function_load(self, url):
soup = get_html(url)
title = BeautifulSoup(soup, 'lxml').find_all(
'h4', {'class': "entry-title-text"})[-1].text
title = title.split('entry')[0]
post = BeautifulSoup(soup, 'lxml').find('div', class_='entry-content')
self.load_post(url, title, post)
return title
def get_list_link_post(self, find_all, find, begining=1, period=1):
list_link_post = BeautifulSoup(get_html(
self.url), 'lxml').find_all(*find_all)[begining:] #\
if find: list_link_post = [i.find(*find) for i in list_link_post]
list_link_post = [i.get('href') for i in list_link_post]
self.list_link_post = [
url for url in list_link_post if url not in PostBlog.lp.list_saves
]
# print(len(self.list_link_post),self.list_link_post)
return len(self.list_link_post)
def get_list_link_post(self, number=None, period=1):
# print("get_list_link_post")
find_all = ('div', {'class': "entry-wrap js-emojis"})
find = ('a', {'class': "subj-link"})
PostBlog.get_list_link_post(self, find_all, find, 0, period)
list_link_post = []
for url in self.list_link_post:
if 'https://p-balaev.livejournal' in url:
title = BeautifulSoup(get_html(url), 'lxml').find_all(
'h4', {'class': "entry-title-text"})[-1].text
if 'Мои твиты' not in title:
list_link_post.append(url)
self.list_link_post = list_link_post[1:number]
# print(len(self.list_link_post), self.list_link_post)
return len(self.list_link_post)
def function_load(self, url):
post = BeautifulSoup(get_html(url), 'lxml').find('div',
class_="main-block")
title = post.find('h1').text
if 'publications' in url:
tag = 'article'
self.creator = post.find('a').text
else:
tag = 'div'
creator = post.find('div', class_="article-item-text").find('em') or \
post.find('div', class_="classics-item-extra-block").find('li')
self.creator = creator.text.strip().replace('„', '').replace(
'“', '').replace('"', '').replace('/', '')
# print(creator)
self.load_post(url, title, post.find(tag, class_="article-item-body"),
self.url)
return title
def function_load(self, url):
soup = BeautifulSoup(get_html(url), 'lxml')
title = soup.find_all('dt', class_="entry-title")[-1].text
post = soup.find('div', class_='entry-content')
self.load_post(url, title, post)
return title
