def parse_entry(self, entry):
"""
Parse an entry in an RSS feed.
"""
entry_url = self.get_url(entry)
# merge description with body
body = self.get_body(entry)
description = self.get_description(entry)
if not body:
body = description
description = None
return {
'id': entry.id,
'url': entry_url,
'domain': url.get_domain(entry_url),
'body': html.prepare(body, entry_url),
'title': self.get_title(entry),
'description': html.prepare(description, entry_url),
'tags': self.get_tags(entry),
'authors': self.get_authors(entry),
'created': self.get_created(entry),
'img_url': self.get_img_url(entry, body),
'links': self.get_links(body, entry_url)
}
def body_via_readability(page_html, source_url):
"""
Readbility is good at article + title.
"""
obj = Document(page_html)
body = obj.summary()
if not body:
return None
return html.prepare(body, source_url)
def body_via_readability(page_html, source_url):
"""
Readbility is good at article + title.
"""
obj = Document(page_html)
body = obj.summary()
if not body:
return None
return html.prepare(body, source_url)
def _prepare_str(o, field, source_url=None):
"""
Prepare text/html field
"""
if field not in o:
return None
if o[field] is None:
return None
if html.is_html(o[field]):
return html.prepare(o[field], source_url)
return text.prepare(o[field])
def prepare_str(o, field, source_url=None):
"""
Prepare text/html field
"""
if field not in o:
return None
if o[field] is None:
return None
if html.is_html(o[field]):
return html.prepare(o[field], source_url)
return text.prepare(o[field])
def body_via_article_tag(soup, source_url):
"""
Extract content from an "article" tag.
"""
if not isinstance(soup, BeautifulSoup):
soup = BeautifulSoup(soup)
articles = soup.find_all('article')
if len(articles):
raw_html = html.get_inner(articles[0])
body = html.prepare(raw_html, source_url)
return body, raw_html
return None, None
def body_via_article_tag(soup, source_url):
"""
Extract content from an "article" tag.
"""
if not isinstance(soup, BeautifulSoup):
soup = BeautifulSoup(soup)
articles = soup.find_all('article')
if len(articles):
raw_html = html.get_inner(articles[0])
body = html.prepare(raw_html, source_url)
return body, raw_html
return None, None
def body_via_embedly(source_url):
"""
Use Embed.ly's API for content extraction.
"""
# make request to embedly api
e = embedly_api.extract(source_url)
# check for errors.
if e['type'] == 'error':
return None
return html.prepare(e.get('content'), source_url)
def body_via_embedly(source_url):
"""
Use Embed.ly's API for content extraction.
"""
# make request to embedly api
e = embedly_api.extract(source_url)
# check for errors.
if e['type'] == 'error':
return None
return html.prepare(e.get('content'), source_url)
def parse_entry(self, entry):
"""
Parse an entry in an RSS feed.
"""
entry_url = self.get_url(entry)
# merge description with body
body = self.get_body(entry)
description = self.get_description(entry)
if not body:
body = description
description = None
return {
'url': entry_url,
'body': html.prepare(body, entry_url),
'title': self.get_title(entry),
'description': html.prepare(description, entry_url),
'tags': self.get_tags(entry),
'authors': self.get_authors(entry),
'created': self.get_created(entry),
'img_url': self.get_img_url(entry, body),
'links': self.get_links(body, entry_url),
}
