def parse_film(self, soup):
belka = soup.find(ct('ps_belka'))
title_pl = tag_text(belka.find('h2'))
title = tag_text(belka.find('h4'))
rows = soup.findAll(ct('row'))
def _row(r):
p = tag_text(r).split(':', 1)
if len(p) == 2:
return p[0].strip(), p[1].strip()
else:
return None, None
props = dict(_row(row) for row in rows)
screenings = soup.find(ct('pokazy'))
screenings = screenings and screenings.findAll('li')[1:]
screenings = screenings and [tag_text(s) for s in screenings] or []
img_url = soup.find(ct('ps_body')).find('img')
img_url = img_url and img_url.parent['href']
return {
'title':title,
'title_localized':title_pl,
# 'props':props,
'directors':filter(bool, [i.strip() for i in props.get(u'Reżyser', '').split(',')]),
'times':[self.parse_t(t) for t in screenings],
'year':props.get('Rok produkcji', None),
'img_url':img_url,
}
def parse_t(self, t):
date = tag_text(t.find(ct('perf_date')))
day = re.match("\w+\s*(\d+)", date).group(1)
h, m = re.match("(\d+):(\d+)", tag_text(t.find(ct('perf_time')))).groups()
venue = tag_text(t.find(ct('perf_venue'))).strip()
theater = self.get_theater(venue)
if not theater:
logger.warning('no theater found for %r', venue)
return
t = self.get_screening_datetime(h, m, day)
return theater, pytz.timezone(theater.timezone_id).localize(t), venue
def parse_t(self, t):
date = tag_text(t.find(ct('perf_date')))
day = re.match("\w+\s*(\d+)", date).group(1)
h, m = re.match("(\d+):(\d+)",
tag_text(t.find(ct('perf_time')))).groups()
venue = tag_text(t.find(ct('perf_venue'))).strip()
theater = self.get_theater(venue)
if not theater:
logger.warning('no theater found for %r', venue)
return
t = self.get_screening_datetime(h, m, day)
return theater, pytz.timezone(theater.timezone_id).localize(t), venue
def films(self):
for i in range(20111012, 20111028):
path = '/lff/calendar/%d' % i
soup = self.get_soup(path)
films = soup.findAll(ct('calendar-teaser-timeblock'))
for f in films:
showtimes = f.findAll(ct('perf_row'))
times = [self.parse_t(t) for t in showtimes]
times = [t for t in times if t]
details = self.get_soup(f.find(ct('show_title')).find('a')['href'])
parsed = self.parse_film(details)
parsed['times'] = times
title = parsed.get('title')
if title:
yield parsed
def films(self):
for i in range(20111012, 20111028):
path = '/lff/calendar/%d' % i
soup = self.get_soup(path)
films = soup.findAll(ct('calendar-teaser-timeblock'))
for f in films:
showtimes = f.findAll(ct('perf_row'))
times = [self.parse_t(t) for t in showtimes]
times = [t for t in times if t]
details = self.get_soup(
f.find(ct('show_title')).find('a')['href'])
parsed = self.parse_film(details)
parsed['times'] = times
title = parsed.get('title')
if title:
yield parsed
def parse_film(self, soup):
title = soup.find(id="header-one-films")
title = title and tag_text(title.find('h1'))
props = soup.findAll(ct('screening-with-credits-item'))
props = dict((tag_text(p.find(ct('screening-with-credits-left'))),
tag_text(p.find(ct('screening-with-credits-right'))))
for p in props)
directors = [i.strip() for i in props.get('Director', '').split(',')]
synopsis = tag_text(soup.find(ct('program-item-alternatetitle')))
try:
year = props.get('Year')
year = year and int(year) or None
except ValueError:
year = None
return {
'title': title,
'directors': filter(bool, directors),
'year': year,
'synopsis': synopsis,
}
def films(self):
for part in ['special'] + [chr(ord('a') + i) for i in range(26)]:
for subpage in range(10):
path = '/filmy/wszystkie/%s/%s/' % (part, subpage)
soup = self.get_soup(path)
films = soup.findAll(ct('nowina'))
if films:
for f in films:
url = '/' + f.find('a')['href']
details = self.get_soup(url)
yield self.parse_film(details)
else:
break
def films(self):
for part in ['special'] + [chr(ord('a') + i) for i in range(26)]:
for subpage in range(10):
path = '/filmy/wszystkie/%s/%s/' % (part, subpage)
soup = self.get_soup(path)
films = soup.findAll(ct('nowina'))
if films:
for f in films:
url = '/' + f.find('a')['href']
details = self.get_soup(url)
yield self.parse_film(details)
else:
break
def parse_film(self, soup):
title = soup.find(id="header-one-films")
title = title and tag_text(title.find('h1'))
props = soup.findAll(ct('screening-with-credits-item'))
props = dict((
tag_text(p.find(ct('screening-with-credits-left'))),
tag_text(p.find(ct('screening-with-credits-right')))
) for p in props)
directors = [i.strip() for i in props.get('Director', '').split(',')]
synopsis = tag_text(soup.find(ct('program-item-alternatetitle')))
try:
year = props.get('Year')
year = year and int(year) or None
except ValueError:
year = None
return {
'title': title,
'directors':filter(bool, directors),
'year':year,
'synopsis':synopsis,
}
def parse_film(self, soup):
belka = soup.find(ct('ps_belka'))
title_pl = tag_text(belka.find('h2'))
title = tag_text(belka.find('h4'))
rows = soup.findAll(ct('row'))
def _row(r):
p = tag_text(r).split(':', 1)
if len(p) == 2:
return p[0].strip(), p[1].strip()
else:
return None, None
props = dict(_row(row) for row in rows)
screenings = soup.find(ct('pokazy'))
screenings = screenings and screenings.findAll('li')[1:]
screenings = screenings and [tag_text(s) for s in screenings] or []
img_url = soup.find(ct('ps_body')).find('img')
img_url = img_url and img_url.parent['href']
return {
'title':
title,
'title_localized':
title_pl,
# 'props':props,
'directors':
filter(bool,
[i.strip() for i in props.get(u'Reżyser', '').split(',')]),
'times': [self.parse_t(t) for t in screenings],
'year':
props.get('Rok produkcji', None),
'img_url':
img_url,
}