def _request(self, url, language=None, data=None):
if self.config.trace_mode:
logger.debug(f"URL: {url}")
if data:
return self.config.post_html(url,
data=data,
headers=util.header(language))
else:
return self.config.get_html(url, headers=util.header(language))
def get_list_description(self, tvdb_url):
response = self.config.get_html(tvdb_url,
headers=util.header(
self.tvdb_language))
description = response.xpath(
"//div[@class='block']/div[not(@style='display:none')]/p/text()")
return description[0] if len(description) > 0 and len(
description[0]) > 0 else ""
def get_list_description(self, list_url, language):
if self.config.trace_mode:
logger.debug(f"URL: {list_url}")
response = self.config.get_html(list_url,
headers=util.header(language))
descriptions = response.xpath(
"//meta[@property='og:description']/@content")
return descriptions[0] if len(descriptions) > 0 and len(
descriptions[0]) > 0 else None
def _tmdb(self, letterboxd_url, language):
if self.config.trace_mode:
logger.debug(f"URL: {letterboxd_url}")
response = self.config.get_html(letterboxd_url,
headers=util.header(language))
ids = response.xpath("//a[@data-track-action='TMDb']/@href")
if len(ids) > 0 and ids[0]:
if "themoviedb.org/movie" in ids[0]:
return util.regex_first_int(ids[0], "TMDb Movie ID")
raise Failed(
f"Letterboxd Error: TMDb Movie ID not found in {ids[0]}")
raise Failed(
f"Letterboxd Error: TMDb Movie ID not found at {letterboxd_url}")
def _ids_from_url(self, tvdb_url):
ids = []
tvdb_url = tvdb_url.strip()
if self.config.trace_mode:
logger.debug(f"URL: {tvdb_url}")
if tvdb_url.startswith((urls["list"], urls["alt_list"])):
try:
response = self.config.get_html(tvdb_url,
headers=util.header(
self.tvdb_language))
items = response.xpath(
"//div[@class='col-xs-12 col-sm-12 col-md-8 col-lg-8 col-md-pull-4']/div[@class='row']"
)
for item in items:
title = item.xpath(
".//div[@class='col-xs-12 col-sm-9 mt-2']//a/text()"
)[0]
item_url = item.xpath(
".//div[@class='col-xs-12 col-sm-9 mt-2']//a/@href")[0]
if item_url.startswith("/series/"):
try:
ids.append(
(self.get_series(f"{base_url}{item_url}").id,
"tvdb"))
except Failed as e:
logger.error(f"{e} for series {title}")
elif item_url.startswith("/movies/"):
try:
movie = self.get_movie(f"{base_url}{item_url}")
if movie.tmdb_id:
ids.append((movie.tmdb_id, "tmdb"))
elif movie.imdb_id:
ids.append((movie.imdb_id, "imdb"))
except Failed as e:
logger.error(e)
else:
logger.error(f"TVDb Error: Skipping Movie: {title}")
time.sleep(2)
if len(ids) > 0:
return ids
raise Failed(f"TVDb Error: No TVDb IDs found at {tvdb_url}")
except requests.exceptions.MissingSchema:
util.print_stacktrace()
raise Failed(f"TVDb Error: URL Lookup Failed for {tvdb_url}")
else:
raise Failed(
f"TVDb Error: {tvdb_url} must begin with {urls['list']}")
def _ids_from_url(self, imdb_url, language, limit):
total, item_count = self._total(imdb_url, language)
headers = util.header(language)
imdb_ids = []
parsed_url = urlparse(imdb_url)
params = parse_qs(parsed_url.query)
imdb_base = parsed_url._replace(query=None).geturl()
params.pop("start", None) # noqa
params.pop("count", None) # noqa
params.pop("page", None) # noqa
if self.config.trace_mode:
logger.debug(f"URL: {imdb_base}")
logger.debug(f"Params: {params}")
search_url = imdb_base.startswith(urls["searches"])
if limit < 1 or total < limit:
limit = total
remainder = limit % item_count
if remainder == 0:
remainder = item_count
num_of_pages = math.ceil(int(limit) / item_count)
for i in range(1, num_of_pages + 1):
start_num = (i - 1) * item_count + 1
logger.ghost(
f"Parsing Page {i}/{num_of_pages} {start_num}-{limit if i == num_of_pages else i * item_count}"
)
if search_url:
params[
"count"] = remainder if i == num_of_pages else item_count # noqa
params["start"] = start_num # noqa
else:
params["page"] = i # noqa
response = self.config.get_html(imdb_base,
headers=headers,
params=params)
ids_found = response.xpath(
"//div[contains(@class, 'lister-item-image')]//a/img//@data-tconst"
)
if not search_url and i == num_of_pages:
ids_found = ids_found[:remainder]
imdb_ids.extend(ids_found)
time.sleep(2)
logger.exorcise()
if len(imdb_ids) > 0:
logger.debug(f"{len(imdb_ids)} IMDb IDs Found: {imdb_ids}")
return imdb_ids
raise Failed(f"IMDb Error: No IMDb IDs Found at {imdb_url}")
def _parse_list(self, list_url, language):
if self.config.trace_mode:
logger.debug(f"URL: {list_url}")
response = self.config.get_html(list_url,
headers=util.header(language))
letterboxd_ids = response.xpath(
"//li[contains(@class, 'poster-container')]/div/@data-film-id")
items = []
for letterboxd_id in letterboxd_ids:
slugs = response.xpath(
f"//div[@data-film-id='{letterboxd_id}']/@data-film-slug")
items.append((letterboxd_id, slugs[0]))
next_url = response.xpath("//a[@class='next']/@href")
if len(next_url) > 0:
time.sleep(2)
items.extend(self._parse_list(f"{base_url}{next_url[0]}",
language))
return items
def _total(self, imdb_url, language):
if imdb_url.startswith(urls["lists"]):
xpath_total = "//div[@class='desc lister-total-num-results']/text()"
per_page = 100
elif imdb_url.startswith(urls["searches"]):
xpath_total = "//div[@class='desc']/span/text()"
per_page = 250
else:
xpath_total = "//div[@class='desc']/text()"
per_page = 50
results = self.config.get_html(
imdb_url, headers=util.header(language)).xpath(xpath_total)
total = 0
for result in results:
if "title" in result:
try:
total = int(
re.findall("(\\d+) title", result.replace(",", ""))[0])
break
except IndexError:
pass
if total > 0:
return total, per_page
raise Failed(f"IMDb Error: Failed to parse URL: {imdb_url}")
def _request(self, url, language, xpath):
if self.config.trace_mode:
logger.debug(f"URL: {url}")
return self.config.get_html(url, headers=util.header(language)).xpath(xpath)
def __init__(self, tvdb_url, language, is_movie, config):
self.tvdb_url = tvdb_url.strip()
self.language = language
self.is_movie = is_movie
self.config = config
if not self.is_movie and self.tvdb_url.startswith(
(urls["series"], urls["alt_series"], urls["series_id"])):
self.media_type = "Series"
elif self.is_movie and self.tvdb_url.startswith(
(urls["movies"], urls["alt_movies"], urls["movie_id"])):
self.media_type = "Movie"
else:
raise Failed(
f"TVDb Error: {self.tvdb_url} must begin with {urls['movies'] if self.is_movie else urls['series']}"
)
if self.config.trace_mode:
logger.debug(f"URL: {tvdb_url}")
response = self.config.get_html(self.tvdb_url,
headers=util.header(self.language))
results = response.xpath(
f"//*[text()='TheTVDB.com {self.media_type} ID']/parent::node()/span/text()"
)
if len(results) > 0:
self.id = int(results[0])
elif self.tvdb_url.startswith(urls["movie_id"]):
raise Failed(
f"TVDb Error: Could not find a TVDb Movie using TVDb Movie ID: {self.tvdb_url[len(urls['movie_id']):]}"
)
elif self.tvdb_url.startswith(urls["series_id"]):
raise Failed(
f"TVDb Error: Could not find a TVDb Series using TVDb Series ID: {self.tvdb_url[len(urls['series_id']):]}"
)
else:
raise Failed(
f"TVDb Error: Could not find a TVDb {self.media_type} ID at the URL {self.tvdb_url}"
)
def parse_page(xpath):
parse_results = response.xpath(xpath)
if len(parse_results) > 0:
parse_results = [
r.strip() for r in parse_results if len(r) > 0
]
return parse_results[0] if len(parse_results) > 0 else None
def parse_title_summary(lang=None):
place = "//div[@class='change_translation_text' and "
place += f"@data-language='{lang}']" if lang else "not(@style='display:none')]"
return parse_page(f"{place}/@data-title"), parse_page(
f"{place}/p/text()[normalize-space()]")
self.title, self.summary = parse_title_summary(lang=self.language)
if not self.title and self.language in language_translation:
self.title, self.summary = parse_title_summary(
lang=language_translation[self.language])
if not self.title:
self.title, self.summary = parse_title_summary()
if not self.title:
raise Failed(
f"TVDb Error: Name not found from TVDb URL: {self.tvdb_url}")
self.poster_path = parse_page(
"//div[@class='row hidden-xs hidden-sm']/div/img/@src")
self.background_path = parse_page(
"(//h2[@class='mt-4' and text()='Backgrounds']/following::div/a/@href)[1]"
)
if self.is_movie:
self.directors = parse_page(
"//strong[text()='Directors']/parent::li/span/a/text()[normalize-space()]"
)
self.writers = parse_page(
"//strong[text()='Writers']/parent::li/span/a/text()[normalize-space()]"
)
self.studios = parse_page(
"//strong[text()='Studio']/parent::li/span/a/text()[normalize-space()]"
)
else:
self.networks = parse_page(
"//strong[text()='Networks']/parent::li/span/a/text()[normalize-space()]"
)
self.genres = parse_page(
"//strong[text()='Genres']/parent::li/span/a/text()[normalize-space()]"
)
tmdb_id = None
imdb_id = None
if self.is_movie:
results = response.xpath("//*[text()='TheMovieDB.com']/@href")
if len(results) > 0:
try:
tmdb_id = util.regex_first_int(results[0], "TMDb ID")
except Failed:
pass
results = response.xpath("//*[text()='IMDB']/@href")
if len(results) > 0:
try:
imdb_id = util.get_id_from_imdb_url(results[0])
except Failed:
pass
if tmdb_id is None and imdb_id is None:
raise Failed(
f"TVDB Error: No TMDb ID or IMDb ID found for {self.title}"
)
self.tmdb_id = tmdb_id
self.imdb_id = imdb_id
