def get_details_of_one_compilation(self, idfa_data, url):
compilation_data = None
film = None
if url in idfa_data.film_id_by_url.keys():
filmid = idfa_data.film_id_by_url[url]
film_file = film_file_format.format(filmid)
if os.path.isfile(film_file):
charset = web_tools.get_charset(film_file)
with open(film_file, 'r', encoding=charset) as f:
compilation_data = f.read()
if compilation_data is None:
print(f'Downloading site of combination program: {url}')
url_reader = web_tools.UrlReader(Globals.error_collector)
compilation_data = url_reader.read_url(url)
if compilation_data is not None:
print(f'Parsing FILM INFO from: {url}')
film = CompilationPageParser(idfa_data, url,
film).feed(compilation_data)
if film is not None:
film_file = film_file_format.format(filmid)
if not os.path.isfile(film_file):
print(f'Writing HTML data of: {film.title}')
with open(film_file, 'w') as f:
f.write(compilation_data)
print(
f'Parsing SCREENINGS of combination program: {film.title}')
ScreeningsParser(idfa_data, film).feed(compilation_data)
else:
Globals.error_collector.add(
'Parsing of COPMBINATION PROGRAM site failed', url)
return film
def get_screenings_of_one_film(self, film_html_file, nff_data):
title = self.film.title
if os.path.isfile(film_html_file):
self.print_debug("-- Analysing premiêre page of title:", title)
premiere_parser = PremierePageParser(self.film, nff_data)
charset = web_tools.get_charset(film_html_file)
with open(film_html_file, 'r', encoding=charset) as f:
text = '\n' + '\n'.join([line for line in f])
premiere_parser.feed(text)
def get_film_details(imagine_data):
for film in imagine_data.films:
html_data = None
film_file = film_file_format.format(film.filmid)
if os.path.isfile(film_file):
charset = web_tools.get_charset(film_file)
with open(film_file, 'r', encoding=charset) as f:
html_data = f.read()
else:
print(f"Downloading site of {film.title}: {film.url}")
html_data = web_tools.UrlReader(Globals.error_collector).load_url(film.url, film_file)
if html_data is not None:
print(f"Analysing html file {film.filmid} of {film.title} {film.url}")
FilmPageParser(imagine_data, film).feed(html_data)
def parse_film_pages(self, nff_data):
for film in nff_data.films:
film_file = film_file_format.format(film.filmid)
print(
f"Now reading {film_file} - {film.title} ({film.duration_str()})"
)
try:
charset = web_tools.get_charset(film_file)
with open(film_file, 'r', encoding=charset) as f:
film_text = f.read()
self.parse_one_film_page(film, film_text, nff_data)
except FileNotFoundError as e:
Globals.error_collector.add(
e, "while parsing film pages in ScreeningsLoader")
def get_films(self, data):
for page_number in range(1, self.page_count + 1):
az_data = None
az_file = az_file_format.format(page_number)
if os.path.isfile(az_file):
charset = web_tools.get_charset(az_file)
with open(az_file, 'r', encoding=charset) as f:
az_data = f.read()
else:
az_page = az_webroot_format.format(page_number)
print(f"Downloading {az_page}.")
url_reader = web_tools.UrlReader(Globals.error_collector)
az_data = url_reader.load_url(az_page, az_file)
parser = AzPageParser(data)
parser.feed(az_data)
def get_details_of_one_film(self, idfa_data, film):
film_data = None
film_file = film_file_format.format(film.filmid)
if os.path.isfile(film_file):
charset = web_tools.get_charset(film_file)
with open(film_file, 'r', encoding=charset) as f:
film_data = f.read()
else:
print(f"Downloading site of {film.title}: {film.url}")
url_reader = web_tools.UrlReader(Globals.error_collector)
film_data = url_reader.load_url(film.url, film_file)
if film_data is not None:
print(f'Parsing FILM INFO of: {film.title}')
filminfo_parser = FilmPageParser(idfa_data, film)
filminfo_parser.feed(film_data)
print(f'Parsing SCREENINGS of: {film.title}')
screenings_parser = ScreeningsParser(idfa_data, film)
screenings_parser.feed(film_data)