def validate_and_extract(self, node: bs4.element):
if node.name == 'a' \
and node.has_attr('data-pin-do') \
and node['data-pin-do'] == 'embedPin'\
and node.has_attr('href'):
return EPinterestPin(node['href'])
return None
def validate_and_extract(self, node: bs4.element):
if isinstance(node, bs4.element.Tag) \
and node.name == 'iframe' and node.has_attr('src')\
and node['src'].startswith('https://www.youtube.com/embed/'):
return EYouTubeVideo(self.__get_youtube_video_id(node['src']))
return None
def validate_and_extract(self, node: bs4.element):
if node.name == 'iframe' and node.has_attr('src')\
and utils.has_domain(node['src'],
r'^https://www\.youtube\.com/embed'):
return EYouTubeVideo(self.__get_youtube_video_id(node['src']))
return None
def validate_and_extract(self, node: bs4.element):
"""Validates if a tag is instagram post tag and
returns the extracted data from the tag in EInstagramPost object"""
if isinstance(node, bs4.element.Tag):
if node.has_attr('class') \
and ('instagram-media' in node['class']
or 'instagram-media-rendered' in node['class']):
return EInstagramPost(
self.__get_instagram_shortcode(node.find('a')['href']))
if node.name == 'iframe' \
and node.has_attr('src') \
and node['src'].startswith('https://instagram.com/'):
return EInstagramPost(
self.__get_instagram_shortcode(node['src']))
return None
def validate_and_extract(self, node: bs4.element):
if node.name == 'img' and node.has_attr('src'):
return self.__create_image(node)
if node.name == 'figure':
img_tag = node.find('img')
if img_tag and img_tag.has_attr('src'):
return self.__create_image(img_tag, node.find('figcaption'))
return None
def validate_and_extract(self, node: bs4.element):
if node.name == 'q' \
and not utils.empty_text(node.text):
cite = None
if node.has_attr('cite'):
cite = node['cite']
quote = Quote(node.text, cite)
return quote
return None
def validate_and_extract(self, node: bs4.element):
video_urls = list()
if node.name == 'video':
if node.has_attr('src'):
video_urls.append(node['src'])
elif node.contents:
for child in node.contents:
if child.name == 'source'\
and child.has_attr('src'):
video_urls.append(child['src'])
if video_urls:
height, width = e_utils.get_media_size(node)
return Video(video_urls, height, width)
if node.name == 'embed' \
and node.has_attr('src') \
and VIDEO_EXTENSIONS_PATTERN.match(node['src']):
video_urls.append(node['src'])
height, width = e_utils.get_media_size(node)
return Video(video_urls, height, width)
return None
def validate_and_extract(self, node: bs4.element):
if isinstance(node, bs4.element.Tag) \
and node.has_attr('class') \
and ('twitter-tweet' in node['class']
or 'twitter-tweet-rendered' in node['class']):
tweet_a_tag = node.find_all('a')
if tweet_a_tag and tweet_a_tag[-1].has_attr('href'):
tweet_url = tweet_a_tag[-1]['href']
tweet_id = tweet_url.split('/')[-1].split('?')[0]
return ETweet(tweet_id)
return None
