def story(self, ref):
ref = self.strip_ref_prefix(ref)
stories = json(lambda x: api_stories(x, self.BASE_DOMAIN),
headers={'Referer': self.BASE_DOMAIN})
if not stories: return False
stories = list(
filter(None, [
i if i.get("audience") == "everyone" else None for i in stories
]))
stories = list(
filter(None,
[i if str(i.get('id')) == ref else None for i in stories]))
if len(stories) == 0:
return False
r = stories[0]
if not r:
return False
s = {}
s['author'] = ''
s['author_link'] = ''
s['date'] = unix(r.get('post_date'))
s['score'] = r.get('reactions').get('❤')
s['title'] = r.get('title', '')
s['link'] = r.get('canonical_url', '')
s['url'] = r.get('canonical_url', '')
comments = json(lambda x: api_comments(x, self.BASE_DOMAIN),
r.get('id'),
headers={'Referer': self.BASE_DOMAIN})
s['comments'] = [] if not comments else [
comment(i) for i in comments.get('comments')
]
s['comments'] = list(filter(bool, s['comments']))
s['num_comments'] = r.get('comment_count', 0)
authors = list(
filter(None, [
self._bylines(byline) for byline in r.get('publishedBylines')
]))
if len(authors):
s['author'] = authors[0].get('name')
s['author_link'] = authors[0].get('link')
markup = xml(lambda x: s['link'])
if markup:
icons = get_icons(markup, url=s['link'])
if icons:
s['icon'] = icons[0]
return s
def get_json_comments(url, markup=None):
regex = r"https:\/\/www\.stuff\.co\.nz\/(.*\/\d+)/[^\/]+"
p = re.compile(regex).match(url)
if not p: return []
path = p.groups()[0]
if not markup:
markup = xml(lambda x: url)
soup = BeautifulSoup(markup, features='html.parser')
scripts = soup.find_all('script', src=True)
scripts = list(filter(None, [s if s['src'].startswith("https://cdns.gigya.com/JS/gigya.js?apiKey=") else None for s in scripts]))
if not scripts: return []
script = scripts[0]
if not script: return []
meh, params = script['src'].split('?', maxsplit=1)
params = params.split('&')
params = [p.split('=') for p in params]
params = list(filter(None, [value if name.lower() == 'apikey' else None for name, value in params]))
if not params: return []
apiKey = params[0]
if not apiKey: return []
url = f"https://comments.us1.gigya.com/comments.getComments?threaded=true&format=json&categoryID=Stuff&streamID=stuff/{path}&APIKey={apiKey}"
data = json(lambda x: url)
comments = data.get('comments', [])
comments = [_parse_json_comment(c) for c in comments]
return comments
def story(self, ref):
ref = self.strip_ref_prefix(ref)
stories = json(SUBSTACK_API_TOP_POSTS,
headers={'Referer': SUBSTACK_REFERER})
if not stories: return False
stories = list(
filter(None, [
i if i.get("audience") == "everyone" else None for i in stories
]))
stories = list(
filter(None,
[i if str(i.get('id')) == ref else None for i in stories]))
if len(stories) == 0:
return False
r = stories[0]
if not r:
return False
s = {}
pub = r.get('pub')
base_url = pub.get('base_url')
s['author'] = pub.get('author_name')
s['author_link'] = author_link(pub.get('author_id'), base_url)
s['date'] = unix(r.get('post_date'))
s['score'] = r.get('score')
s['title'] = r.get('title', '')
s['link'] = r.get('canonical_url', '')
s['url'] = r.get('canonical_url', '')
comments = json(lambda x: api_comments(x, base_url),
r.get('id'),
headers={'Referer': base_url})
s['comments'] = [] if not comments else [
comment(i) for i in comments.get('comments')
]
s['comments'] = list(filter(bool, s['comments']))
s['num_comments'] = r.get('comment_count', 0)
return s
def feed(self):
too_old = datetime.now().timestamp() - settings.MAX_STORY_AGE
stories = json(lambda x: api_stories(x, self.BASE_DOMAIN),
headers={'Referer': self.BASE_DOMAIN})
if not stories: return []
stories = list(
filter(None, [
i if i.get("audience") == "everyone" else None for i in stories
]))
stories = list(
filter(None, [
i if unix(i.get('post_date')) > too_old else None
for i in stories
]))
stories.sort(key=lambda a: unix(a.get('post_date')), reverse=True)
return [self.ref_prefix(str(i.get("id"))) for i in stories or []]
def feed(self):
too_old = datetime.now().timestamp() - settings.MAX_STORY_AGE
stories = json(SUBSTACK_API_TOP_POSTS,
headers={'Referer': SUBSTACK_REFERER})
if not stories: return []
stories = list(
filter(None, [
i if i.get("audience") == "everyone" else None for i in stories
]))
stories = list(
filter(None, [
i if unix(i.get('post_date')) > too_old else None
for i in stories
]))
stories.sort(key=lambda a: unix(a.get('post_date')), reverse=True)
stories = [
self.ref_prefix(str(i.get("pub").get("base_url")),
str(i.get("id"))) for i in stories
]
return stories