def parse_medium(self, medium, sensitive):
'''
Helper function to parse a medium
'''
medium_class_type = medium.get('class', '')[0]
medium_type = medium_class_type[3:medium_class_type.index("--")]
if (medium_type == "image"):
return Medium(image_src=htmlParser.get_image_src(
medium, {'class': "mc-image--wrapper"}, html_tag="div"),
medium_type=medium_type,
sensitive=sensitive)
image_src = htmlParser.get_image_src(
medium, {'class': f"mc-{medium_type}--image"}, html_tag="div")
title = htmlParser.get_text(medium, 'span',
{'class': f"mc-{medium_type}--title"})
excerpt = htmlParser.get_text(medium, 'span',
{'class': f"mc-{medium_type}--excerpt"})
link_element = htmlParser.get_element_by_css(
medium, f'span.mc-{medium_type}--link')
link_src = None if link_element is None else htmlParser.get_text(
link_element, 'a', {}).strip()
return Medium(image_src=image_src,
title=title,
excerpt=excerpt,
link_src=link_src,
medium_type=medium_type,
sensitive=sensitive)
def get_description(self):
'''
Parses the profile page to get the "profile--bio" to get the user profile description as well as any hashtags inside.
Returns (str, Hashtags)
'''
return htmlParser.get_text(self.profile_page, 'span',
{'class': 'profile--bio'})
def get_username(self):
username = htmlParser.get_text(self.profile_page, 'span',
{'class': 'profile--username'})
if (username is not None and not username.startswith("@")):
username = "******" + username
return username
def get_view_count(self):
return htmlParser.get_text(self.post, 'span',
{'class': 'impressions--count'})
def get_timestamp(self):
self.timestamp = htmlParser.get_text(self.post, 'span',
{'class': 'post--timestamp'})
return self.timestamp
def get_name(self):
return htmlParser.get_text(self.echo_by, 'span',
{'class': 'reblock'})[10:]
def get_username(self):
return htmlParser.get_text(self.post, 'span',
{'class': 'author--username'})
def get_name(self):
return htmlParser.get_text(self.profile_page, 'span',
{'class': 'profile--name'})
def get_upvote_count(self):
return htmlParser.get_text(self.post_element,
'span', {'class': 'pa--item--count'},
index=2)
def get_created_at_from_echo_no_reply(self):
timestamp = htmlParser.get_element_by_css(self.post_element,
'div.eb--timestamp')
return htmlParser.get_text(timestamp, 'span', {})