def __get_item_content(article: ResultSet):
content = article.find('div', class_="text-container")
if content is None:
content = article.find('p', class_=None, recursive=True)
if content is not None:
return content.getText().strip()
else:
return None
def __get_item_author(article: ResultSet):
author = article.find(class_="author-block__info", recursive=True)
if author is None:
author = article.find(class_="story-block__byline", recursive=True)
if author is not None:
return author.getText().strip()
else:
return None
def __get_item_content(article: ResultSet):
content = article.find('p', class_="story-block__standfirst", recursive=True)
if content is None:
content = article.find('p', class_="standfirst-content", recursive=True)
if content is None:
content = article.find('p', class_=None)
if content is not None:
return content.getText().strip()
else:
return None
def __get_item_url(article: ResultSet):
headline_elem = AbcNewsItemParser.__get_headline_elem(article)
# Not all articles use a common headline element, so get first link if no dedicated headline encountered
if headline_elem is None:
return article.find('a')['href']
else:
return headline_elem.find('a')['href']
def get_price(self, listing: element.ResultSet) -> str:
"""Gets a price of an apartment from a "li" element passed in
by finding the first "div" element.
:param listing: "li" element for one apartment
:type listing: element.ResultSet
:return: price of an apartment
:rtype: str
"""
price = listing.find("div", class_="price").text
return price
def get_listing_link(self, listing: element.ResultSet) -> str:
"""Gets a link of a listing from a "li" element passed in
by finding the first "a" element.
:param listing: "li" element for one apartment
:type listing: element.ResultSet
:return: a link to a listing
:rtype: str
"""
listing_link = listing.find("a")["href"]
return listing_link
def get_title(self, listing: element.ResultSet) -> str:
"""Gets a title of a listing from a "li" element passed in
by finding the first "h2" element.
:param listing: "li" element for one apartment
:type listing: element.ResultSet
:return: title of an apartment's listing
:rtype: str
"""
title = listing.find("h2", class_="title-list").text
return title
def get_attribute(self, listing: element.ResultSet, attribute_name: str) -> str:
""" "Gets table row value by searching for corresponding keys which are
passsed in as an attribute_name.
:param listing: "li" element for one apartment
:type listing: element.ResultSet
:param attribute_name: a keyword to search for in a li element
:type attribute_name: str
:return: value that corresponds to a keyword
:rtype: str
"""
sq_meters = listing.find("span", title=attribute_name).text
return sq_meters
def __get_topic_text(article: ResultSet):
topic = article.find(class_="story-block__kicker")
if topic is not None:
return topic.getText().strip()
else:
return None
def __get_item_url(article: ResultSet):
headline = TheAustralianNewsItemParser.__get_headline_elem(article)
if headline is None:
return article.find('a')['href']
else:
return headline.find('a')['href']
def __get_headline_elem(article: ResultSet):
# Article can sometimes have no headline, e.g. in Daily Cartoon
return article.find(class_="story-block__heading")
def _find_advert_anhor(self, div: element.ResultSet) -> element.Tag:
""" Function which search for an anhor in div. """
return div.find('a', {'href': True, 'class': True, 'title': False})
def __get_headline_elem(article: ResultSet):
headline_elem = article.find(class_='headline', recursive=True)
return headline_elem
def __get_headline_text(article: ResultSet):
headline_elem = AbcNewsItemParser.__get_headline_elem(article)
# Not all articles use a common headline element, if not found get the link text
if headline_elem is None:
headline_elem = article.find('a')
return headline_elem.getText().strip()
def __get_headline_elem(article: ResultSet):
headline_elem = article.find('h3')
return headline_elem
def __get_item_url(article: ResultSet):
return article.find('a', class_="story__link")['href']
def __get_headline_text(article: ResultSet):
return article.find(class_="story__headline__text").getText().strip()
def __get_topic_text(article: ResultSet):
topic = article.find(class_="topic__string")
if topic is not None:
return topic.getText().strip()
else:
return None
def __get_item_author(article: ResultSet):
byline = article.find(class_='byline')
if byline is not None:
return byline.find('a').getText().strip()
else:
return None