def _parse_row(self, row, tags=None):
movie_el = row.cssselect_first('.movie a:not(.tag)')
url = movie_el.link()
title = movie_el.text_content()
date_el = row.cssselect_first('.date').text_content(whitespace=True)
date, time = re.split(r'[\r\n]+', date_el)
starts_at = times.to_universal(datetime.datetime.combine(
parsers.date_cs(date),
datetime.time(*[int(n) for n in time.split(':')])
), 'Europe/Prague')
tags = self._parse_tags(row, tags)
details = self._parse_details(url)
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main_scraped=title,
url=url,
**details
),
starts_at=starts_at,
tags=tags,
url=self.url,
)
def _parse_row(self, row, tags=None):
movie_el = row.cssselect_first('.movie a:not(.tag)')
url = movie_el.link()
title = movie_el.text_content()
date_el = row.cssselect_first('.date').text_content(whitespace=True)
date, time = re.split(r'[\r\n]+', date_el)
starts_at = times.to_universal(
datetime.datetime.combine(
parsers.date_cs(date),
datetime.time(*[int(n) for n in time.split(':')])),
'Europe/Prague')
tags = self._parse_tags(row, tags)
details = self._parse_details(url)
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(title_main_scraped=title,
url=url,
**details),
starts_at=starts_at,
tags=tags,
url=self.url,
)
def __call__(self):
date = None
for row in self._scrape_rows():
if row.element.has_class('day'):
date = parsers.date_cs(row.element.text_content())
else:
yield self._parse_row(row.element, date, row.url)
def __call__(self):
date = None
for row in self._scrape_rows():
if row.element.has_class('day'):
date = parsers.date_cs(row.element.text_content())
else:
yield self._parse_row(row.element, date, row.url)
def __call__(self):
resp = self.session.get(self.url)
html = parsers.html(resp.content, base_url=resp.url)
for event in html.cssselect('.event'):
header = event.cssselect_first('h2')
url = header.link()
title = header.text_content()
title_parts = title.split('/')
if len(title_parts) == 2:
# naive, but for now good enough
title_main, title_orig = title_parts
else:
title_main = title
title_orig = None
details = event.cssselect_first('.descshort').text_content()
cat = event.cssselect_first('.title-cat').text_content().lower()
tags = []
for regexp, tag in self.tag_re:
if regexp.search(title_main):
tags.append(tag)
title_main = regexp.sub('', title_main).strip()
if title_orig and regexp.search(title_orig):
tags.append(tag)
title_orig = regexp.sub('', title_orig).strip()
if regexp.search(details):
tags.append(tag)
if cat != 'filmy':
tags.append(cat)
d = parsers.date_cs(
event.cssselect_first('.nextdate strong').text
)
t = event.cssselect_first('.nextdate .evttime').text_content()
t = time(*map(int, t.split(':')))
starts_at = times.to_universal(datetime.combine(d, t), self.tz)
yield Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main_scraped=title_main,
title_orig=title_orig or None,
),
starts_at=starts_at,
url=url,
url_booking=self.url_booking,
tags={tag: None for tag in tags},
)
def __call__(self):
resp = self.session.get(self.url)
html = parsers.html(resp.content, base_url=resp.url)
for event in html.cssselect('.event'):
header = event.cssselect_first('h2')
url = header.link()
title = header.text_content()
title_parts = title.split('/')
if len(title_parts) == 2:
# naive, but for now good enough
title_main, title_orig = title_parts
else:
title_main = title
title_orig = None
details = event.cssselect_first('.descshort').text_content()
cat = event.cssselect_first('.title-cat').text_content().lower()
tags = []
for regexp, tag in self.tag_re:
if regexp.search(title_main):
tags.append(tag)
title_main = regexp.sub('', title_main).strip()
if title_orig and regexp.search(title_orig):
tags.append(tag)
title_orig = regexp.sub('', title_orig).strip()
if regexp.search(details):
tags.append(tag)
if cat != 'filmy':
tags.append(cat)
d = parsers.date_cs(event.cssselect_first('.nextdate strong').text)
t = event.cssselect_first('.nextdate .evttime').text_content()
t = time(*map(int, t.split(':')))
starts_at = times.to_universal(datetime.combine(d, t), self.tz)
yield Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main_scraped=title_main,
title_orig=title_orig or None,
),
starts_at=starts_at,
url=url,
url_booking=self.url_booking,
tags={tag: None
for tag in tags},
)
def _parse_item(self, item):
title_main = item.cssselect_first('.program-title').text_content()
url = item.cssselect_first('.program-title').link()
date_el = item.cssselect_first('.program-date').text_content()
date, time = re.split(r'\s+ve?\s+', date_el)
starts_at = times.to_universal(
datetime.datetime.combine(
parsers.date_cs(date),
datetime.time(*[int(n) for n in time.split(':')])),
'Europe/Prague')
details = self._parse_details(url)
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(title_main_scraped=title_main,
url=url,
**details),
starts_at=starts_at,
url=self.url,
)
def _parse_item(self, item):
title_main = item.cssselect_first('.program-title').text_content()
url = item.cssselect_first('.program-title').link()
date_el = item.cssselect_first('.program-date').text_content()
date, time = re.split(r'\s+ve?\s+', date_el)
starts_at = times.to_universal(datetime.datetime.combine(
parsers.date_cs(date),
datetime.time(*[int(n) for n in time.split(':')])
), 'Europe/Prague')
details = self._parse_details(url)
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main_scraped=title_main,
url=url,
**details
),
starts_at=starts_at,
url=self.url,
)
