def _parse_event(self, event):
starts_at = times.to_universal(event.get('dtstart').dt)
title_main = event.get('summary')
titles = [title_main]
title_orig = year = length = None
tags = []
match = self.desc_re.match(event.get('description'))
if match:
if match.group('title'):
title_orig = match.group('title').strip()
titles.append(title_orig)
year = int(match.group('year'))
length = int(match.group('min'))
tags = [
self.tags_map.get(t.strip())
for t in match.group('tags').split(',')
]
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main=title_main,
title_orig=title_orig,
titles=titles,
year=year,
length=length,
),
starts_at=starts_at,
tags=tags,
)
def _parse_row(self, row):
starts_at = parsers.date_time_year(row[1].text_content(),
row[2].text_content())
title_main = row[3].text_content()
title_orig = row[4].text_content()
# TODO scrape tags according to new implementation of tags
# presented in https://github.com/honzajavorek/zitkino.cz/issues/97
tags = [
self.tags_map.get(t)
for t in (row[5].text_content(), row[6].text_content())
]
url_booking = row[8].link()
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main_scraped=title_main,
title_orig_scraped=title_orig,
),
starts_at=starts_at,
tags={tag: None
for tag in tags if tag},
url=self.url,
url_booking=url_booking,
)
def _parse_row(self, row):
starts_at = parsers.date_time_year(row[1].text_content(),
row[2].text_content())
title_main = row[3].text_content()
title_orig = row[4].text_content()
tags = [
self.tags_map.get(t)
for t in (row[5].text_content(), row[6].text_content())
]
url_booking = row[8].link()
price = parsers.price(row[7].text_content())
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main=title_main,
titles=[title_main, title_orig],
),
starts_at=starts_at,
tags=tags,
url_booking=url_booking,
price=price,
)
def _parse_event(self, event):
starts_at = times.to_universal(event.get('dtstart').dt)
title_main = event.get('summary')
title_orig = year = length = None
tags = []
match = self.desc_re.match(event.get('description'))
if match:
if match.group('title'):
title_orig = match.group('title').strip()
year = int(match.group('year'))
length = int(match.group('min'))
# TODO scrape tags according to new implementation of tags
# presented in https://github.com/honzajavorek/zitkino.cz/issues/97
tags = [
self.tags_map.get(t.strip())
for t in match.group('tags').split(',')
]
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main_scraped=title_main,
title_orig_scraped=title_orig,
year=year,
length=length,
),
starts_at=starts_at,
tags={tag: None
for tag in tags if tag},
url='http://kinonadobraku.cz',
)
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, date, url):
"""Takes single row and date information, returns
:class:`~zitkino.models.Showtime` object.
"""
st = Showtime(cinema=cinema, url=url)
tags = {}
for cell in row:
if cell.has_class('col_time_reservation'):
st.starts_at = self._parse_time(cell, date)
st.url_booking = cell.link()
if cell.has_class('col_movie_name'):
info = self._parse_info(cell)
st.film_scraped = ScrapedFilm(title_main_scraped=info.title,
url=info.url,
**self._parse_details(info.url))
tags.update({tag: None for tag in info.tags})
if cell.has_class('col_param_icons'):
tags.update(self._parse_tags_from_icons(cell))
if cell.has_class('col_cycle'):
tags.update(self._parse_tags_from_cycles(cell))
st.tags = tags
return st
def _parse_row(self, row, subrow, tags=None):
elements = self._parse_subrow(subrow)
title_el = elements.get('title')
if title_el is None:
return None
title_main = title_el.text_content()
if title_main in self.title_blacklist:
return None
starts_at = parsers.date_time_year(
row.cssselect('.film_table_datum')[0].text_content(),
subrow.cssselect('.cas')[0].text_content(),
)
booking_el = elements.get('booking')
url_booking = booking_el.link() if booking_el is not None else None
tags = tags or []
tag_el = elements.get('tag')
if tag_el is not None:
tags.append(self.tags_map.get(tag_el.text_content()))
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main=title_main,
titles=[title_main],
),
starts_at=starts_at,
tags=tags,
url_booking=url_booking,
)
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_entry(self, entry):
try:
description = next(
line for line
in entry.text_content(whitespace=True).splitlines()
if self.length_re.search(line)
)
except StopIteration:
return None # it's not a film
date_el = entry.cssselect_first('h4 span')
date = datetime.datetime(*reversed(
[int(n) for n in date_el.text_content().split('.')]
))
time_el = entry.cssselect_first('.start')
time_match = self.time_re.search(time_el.text_content())
time = datetime.time(
int(time_match.group(1)),
int(time_match.group(2)),
)
starts_at = times.to_universal(
datetime.datetime.combine(date, time),
'Europe/Prague'
)
title = date_el.tail
tags = {}
detail_data = {}
details = [detail.strip() for detail in description.split(',')]
for detail in details:
if self.year_re.match(detail):
detail_data['year'] = int(detail)
match = self.length_re.match(detail)
if match:
detail_data['length'] = int(match.group(1))
if 'tit.' in detail or 'titulky' in detail or 'dabing' in detail:
tags[detail] = None
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main_scraped=title,
**detail_data
),
starts_at=starts_at,
tags=tags,
url=self.url,
)
def _parse_row(self, day, row, labels):
a = row.cssselect_first('a.featureLink')
title = a.text_content()
url = a.link()
details = self._parse_details(url)
tags = {}
showtimes = []
row = list(row.iterchildren())[1:]
labels = list(labels.iterchildren())[1:]
table = [(c.text_content(), l.text_content())
for (c, l) in zip(row, labels)]
for cell, label in table:
if label:
if label == 'Min.':
details.setdefault('length', int(cell))
elif cell != '---':
tags[cell] = label
elif cell:
showtimes.extend(cell.split())
for regexp, tag in self.tag_re:
if regexp.search(title):
tags[tag] = None
title = regexp.sub('', title).strip()
for st in showtimes:
starts_at = times.to_universal(
datetime.datetime.combine(
day, datetime.time(*[int(n) for n in st.split(':')])),
'Europe/Prague')
yield Showtime(
cinema=self.cinema,
film_scraped=ScrapedFilm(title_main_scraped=title, **details),
starts_at=starts_at,
tags=tags,
url='http://www.cinemacity.cz/',
)
def _parse_entry_text(self, title_text, details_text):
"""Takes HTML element with film header line and generates showtimes."""
for title_text, dates_text in self._split_entry_text(title_text):
info = self._parse_info(title_text, details_text)
date_ranges = self._parse_date_ranges(dates_text)
standalone_dates = self._parse_standalone_dates(dates_text)
dates = list(date_ranges) + list(standalone_dates)
for starts_at in dates:
yield Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main_scraped=info.title_main,
directors=info.directors,
),
starts_at=starts_at,
url=self.url,
url_booking=self.url_booking,
tags={tag: None
for tag in info.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_row(self, row, subrow, tags=None):
elements = self._parse_subrow(subrow)
title_el = elements.get('title')
if title_el is None:
return None
title_main = title_el.text_content()
if title_main in self.title_blacklist:
return None
url = title_el.link()
starts_at = parsers.date_time_year(
row.cssselect('.film_table_datum')[0].text_content(),
subrow.cssselect('.cas')[0].text_content(),
)
booking_el = elements.get('booking')
url_booking = booking_el.link() if booking_el is not None else None
tags = {tag: self.tags[tag] for tag in (tags or [])}
tag_el = elements.get('tag')
if tag_el is not None:
tags.update([self._parse_tag(tag_el)])
return Showtime(
cinema=cinema,
film_scraped=ScrapedFilm(
title_main_scraped=title_main,
url=url,
),
starts_at=starts_at,
tags=tags,
url=self.url,
url_booking=url_booking,
)