def getEntriesFromUrl(url, delay=10):
# print("Starting")
try:
page = helper.urlopen(url, delay=delay)
except:
logging.error("Failed to open url: " + url)
return []
# print("Downloaded")
html = page.read()
soup = BeautifulSoup(html, "html.parser")
result = []
baslik_id = soup.find('h1', id='title').attrs['data-id']
# baslik_id = soup.find('h1', id='title').attrs['data-slug']
baslikText = soup.find('h1', id='title').attrs['data-title'].strip()
for j in soup.find('ul', id='entry-list').find_all('li'):
# import re
# i = re.sub('<br\s*?>', '\n', i)
# i = j.find('article')
i = j
# number = int(j.attrs['value'])
id_ = str(i.attrs['data-id'])
text = textWithNewlines(i.find('div', class_='content'))
text = text.strip()
author = str(i.attrs['data-author'])
# author = i.find('span', itemprop='name').getText().strip()
favoriteCount = int(i.attrs['data-favorite-count'])
# date = i.find('a',class_='entry-date').find('time',class_='creation-time').attrs['datetime']
dateText = i.find('a',class_='entry-date').text
try:
timestamp = helper.datetimeToTimestamp(getDatetimesFromEntryDate(dateText)[0])
except:
timestamp = None
# datetimeObject = datetime.datetime.strptime(date, '%Y-%m-%dT%H:%M:%S')
# text = " ".join(i.find_all(text=lambda t: True)).encode('utf-8').strip()
result.append(Entry(text = text,
author = author,
timestamp = timestamp,
baslik_id = baslik_id,
favoriteCount = favoriteCount,
id_ = id_))
return result
def setTimestamp(self, dt):
self.timestamp = helper.datetimeToTimestamp(dt)
