Plex-Meta-Manager/modules/letterboxd.py

77 lines
3.4 KiB
Python
Raw Normal View History

2021-03-10 16:51:27 +00:00
import logging, requests
2021-03-04 20:05:51 +00:00
from lxml import html
from modules import util
from modules.util import Failed
from retrying import retry
logger = logging.getLogger("Plex Meta Manager")
2021-03-30 05:50:53 +00:00
builders = ["letterboxd_list", "letterboxd_list_details"]
2021-03-04 20:05:51 +00:00
class LetterboxdAPI:
2021-03-12 23:16:26 +00:00
def __init__(self, config):
self.config = config
2021-03-04 20:05:51 +00:00
self.url = "https://letterboxd.com"
@retry(stop_max_attempt_number=6, wait_fixed=10000)
2021-03-08 21:54:19 +00:00
def send_request(self, url, language):
2021-03-11 21:51:02 +00:00
return html.fromstring(requests.get(url, headers={"Accept-Language": language, "User-Agent": "Mozilla/5.0 x64"}).content)
2021-03-08 21:54:19 +00:00
def get_list_description(self, list_url, language):
descriptions = self.send_request(list_url, language).xpath("//meta[@property='og:description']/@content")
return descriptions[0] if len(descriptions) > 0 and len(descriptions[0]) > 0 else None
2021-03-04 20:05:51 +00:00
2021-03-12 19:49:23 +00:00
def parse_list(self, list_url, language):
2021-03-08 21:54:19 +00:00
response = self.send_request(list_url, language)
2021-03-12 19:49:23 +00:00
letterboxd_ids = response.xpath("//div[@class='poster film-poster really-lazy-load']/@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]))
2021-03-04 20:05:51 +00:00
next_url = response.xpath("//a[@class='next']/@href")
if len(next_url) > 0:
2021-03-12 19:49:23 +00:00
items.extend(self.parse_list(f"{self.url}{next_url[0]}", language))
return items
2021-03-04 20:05:51 +00:00
def get_tmdb_from_slug(self, slug, language):
return self.get_tmdb(f"{self.url}{slug}", language)
def get_tmdb(self, letterboxd_url, language):
2021-03-08 21:54:19 +00:00
response = self.send_request(letterboxd_url, language)
2021-03-12 19:49:23 +00:00
ids = response.xpath("//a[@data-track-action='TMDb']/@href")
2021-03-11 21:51:02 +00:00
if len(ids) > 0 and ids[0]:
2021-03-12 19:49:23 +00:00
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]}")
2021-03-11 21:53:43 +00:00
raise Failed(f"Letterboxd Error: TMDb Movie ID not found at {letterboxd_url}")
2021-03-04 20:05:51 +00:00
def get_items(self, method, data, language, status_message=True):
pretty = util.pretty_names[method] if method in util.pretty_names else method
movie_ids = []
if status_message:
logger.info(f"Processing {pretty}: {data}")
2021-03-12 19:49:23 +00:00
items = self.parse_list(data, language)
total_items = len(items)
if total_items == 0:
2021-03-04 20:05:51 +00:00
raise Failed(f"Letterboxd Error: No List Items found in {data}")
length = 0
2021-03-12 19:49:23 +00:00
for i, item in enumerate(items, 1):
length = util.print_return(length, f"Finding TMDb ID {i}/{total_items}")
tmdb_id = None
expired = None
2021-03-12 23:16:26 +00:00
if self.config.Cache:
tmdb_id, expired = self.config.Cache.query_letterboxd_map(item[0])
2021-03-12 19:49:23 +00:00
if not tmdb_id or expired is not False:
try:
tmdb_id = self.get_tmdb_from_slug(item[1], language)
except Failed as e:
logger.error(e)
2021-03-12 19:54:13 +00:00
continue
2021-03-13 01:54:53 +00:00
if self.config.Cache:
2021-03-12 23:16:26 +00:00
self.config.Cache.update_letterboxd(expired, item[0], tmdb_id)
2021-03-12 19:49:23 +00:00
movie_ids.append(tmdb_id)
util.print_end(length, f"Processed {total_items} TMDb IDs")
2021-03-04 20:05:51 +00:00
if status_message:
logger.debug(f"TMDb IDs Found: {movie_ids}")
return movie_ids, []