def _find_extra(tag: Tag) -> str:
extra_tag = tag.find('h4', {'class': 'extra'})
if extra_tag is None:
return ''
extra = ParserUtil.remove_children_text_from(extra_tag, extra_tag.text)
extra = VeraParser._add_sup_text_from_text(extra_tag, extra)
return ParserUtil.sanitize_text(extra)
def _transform(venue: Venue, tag: Tag) -> Event:
source = venue.source_url
url = tag.find('a', {'class': 'event-link'})['href']
artist_tag = tag.find('h3', {'class': re.compile(r'artist|artist ')})
if artist_tag is not None:
artist = ParserUtil.remove_children_text_from(
artist_tag, artist_tag.text)
artist = VeraParser._add_sup_text_from_text(artist_tag, artist)
artist = ParserUtil.sanitize_text(artist)
else:
artist = url
extra = VeraParser._find_extra(tag)
extra_title = tag.find('h4', {'class': 'pretitle'})
if extra_title is not None:
extra_title = f'({ParserUtil.sanitize_text(extra_title.text)})'
else:
extra_title = ''
when_tag = tag.find('div', {'class': 'date'})
if when_tag is not None:
when = ParserUtil.remove_children_text_from(
when_tag, when_tag.text)
when = ParserUtil.sanitize_text(when)
when_time = tag.find('div', {'class': 'schedule'}).text
when_time = when_time[when_time.find('start: ') +
7:when_time.find('start: ') + 12]
when_date: datetime = dateparser.parse(
f'{when} {when_time}{venue.timezone_short}', languages=['nl'])
else:
when_date = datetime.min
image_url = tag.find('div', {'class': 'artist-image'})['style']
image_url_end = image_url.find('\'', image_url.find('https') + 4)
image_url = image_url[image_url.find('https'):image_url_end]
when_date = when_date if when_date is not None else datetime.now()
return Event(
url=url,
title=f'{artist} {extra_title}'.strip(),
description=
f'{artist}{" with support" if extra != "" else ""} {extra}'.strip(
),
venue=venue,
source=source,
date_published=datetime.now(),
when=when_date,
image_url=image_url)
def parse(self, parsing_context: ParsingContext) -> List[Event]:
venue = parsing_context.venue
source = venue.source_url
content = json.loads(parsing_context.content)
results = []
for day in content:
events = [
event for event in day['events'] if event['type'] == 'event'
]
for event in events:
description = MelkwegParser._make_description(event)
date = datetime.fromtimestamp(
int(event['date']), pytz.timezone("Europe/Amsterdam"))
title = event['name']
image_url = f'https://s3-eu-west-1.amazonaws.com/static.melkweg.nl/uploads/images/' \
f'scaled/agenda_thumbnail/{event["thumbnail"]}'
url = f'https://www.melkweg.nl/nl/agenda/{event["slug"]}'
results.append(
Event(url=url,
title=title,
description=ParserUtil.sanitize_text(
description[:1400]),
venue=venue,
source=source,
date_published=datetime.now(),
when=date,
image_url=image_url))
logging.getLogger(__name__).info('parsed %d events melkweg',
len(results))
return results
def _transform(venue: Venue, data: Dict) -> Event:
source = venue.source_url
tz_short = venue.timezone_short
url = f'https://www.paradiso.nl/en/program/{data["slug"]}/{data["id"]}'
title = data['title']
description = data['subtitle']
description = description if ParserUtil.not_empty(
description) else title
when_format = f'{data["start_date_time"]}{tz_short}'
when = dateparser.parse(when_format, languages=['en'])
return Event(url=url,
title=title,
description=description,
venue=venue,
source=source,
date_published=datetime.now(),
when=when)
def _transform(venue: Venue, article: Tag) -> Event:
source = venue.source_url
base_url = venue.url
url = article.a.get('href')
content = article.find('div', {'class': 'program__content'})
figure = article.find('figure').img.get('data-src')
date = article.find('time')
title = content.h1
content_title = title.text if title.find('span') is None else \
title.text.replace(title.span.text, '') + ' - ' + title.span.text
description = ParserUtil.stripped_text_or_default_if_empty(
content.p, content_title)
return Event(url=url,
title=content_title,
description=description,
venue=venue,
image_url=f'{base_url}{figure}',
source=source,
date_published=datetime.now(),
when=datetime.fromisoformat(date.get('datetime')))
def _transform(venue: Venue, data: Dict) -> Event:
source = venue.source_url
tz_short = venue.timezone_short
url = data['link']
title = data['title']
image_url = data['image']
description = data['subtitle']
description = description if ParserUtil.not_empty(
description) else title
when_format = f'{data["day"]} {data["month"]} {data["year"]} 00:00{tz_short}'
when = dateparser.parse(when_format, languages=['nl'])
return Event(url=url,
title=title,
description=description,
venue=venue,
image_url=image_url,
source=source,
date_published=datetime.now(),
when=when)
def _add_sup_text_from_text(parent_tag: Tag, text: str) -> str:
sup = parent_tag.find('sup')
return f'{text} ({sup.text})' if ParserUtil.has_non_empty_text(
sup) else text