add imdb scraper

This commit is contained in:
doubaniux 2021-02-18 15:44:10 +01:00
parent 6b07963b51
commit b192f32d4d
5 changed files with 118 additions and 7 deletions

View file

@ -21,6 +21,7 @@ class SourceSiteEnum(models.TextChoices):
IN_SITE = "in-site", CLIENT_NAME
DOUBAN = "douban", _("豆瓣")
SPOTIFY = "spotify", _("Spotify")
IMDB = "imdb", _("IMDb")
class Entity(models.Model):

View file

@ -9,7 +9,7 @@ import time
from lxml import html
from mimetypes import guess_extension
from threading import Thread
from boofilsic.settings import LUMINATI_USERNAME, LUMINATI_PASSWORD, DEBUG
from boofilsic.settings import LUMINATI_USERNAME, LUMINATI_PASSWORD, DEBUG, IMDB_API_KEY
from boofilsic.settings import SPOTIFY_CREDENTIAL
from django.utils import timezone
from django.utils.translation import ugettext_lazy as _
@ -645,7 +645,6 @@ spotify_token_expire_time = time.time()
class SpotifyTrackScraper(AbstractScraper):
site_name = SourceSiteEnum.SPOTIFY.value
# API URL
host = 'https://open.spotify.com/track/'
data_class = Song
form_class = SongForm
@ -918,3 +917,100 @@ def invoke_spotify_token():
# minus 2 for execution time error
spotify_token_expire_time = int(data['expires_in']) + time.time() - 2
spotify_token = data['access_token']
class ImdbMovieScraper(AbstractScraper):
site_name = SourceSiteEnum.IMDB.value
host = 'https://www.imdb.com/title/'
data_class = Movie
form_class = MovieForm
regex = re.compile(r"(?<=https://www\.imdb\.com/title/)[a-zA-Z0-9]+")
def scrape(self, url):
effective_url = self.get_effective_url(url)
if effective_url is None:
raise ValueError("not valid url")
api_url = self.get_api_url(effective_url)
r = requests.get(api_url)
res_data = r.json()
if not res_data['type'] in ['Movie', 'TVSeries']:
raise ValueError("not movie/series item")
if res_data['type'] == 'Movie':
is_series = False
elif res_data['type'] == 'TVSeries':
is_series = True
title = res_data['title']
orig_title = res_data['originalTitle']
imdb_code = self.regex.findall(effective_url)[0]
director = []
for direct_dict in res_data['directorList']:
director.append(direct_dict['name'])
playwright = []
for writer_dict in res_data['writerList']:
playwright.append(writer_dict['name'])
actor = []
for actor_dict in res_data['actorList']:
actor.append(actor_dict['name'])
genre = res_data['genres'].split(', ')
area = res_data['countries'].split(', ')
language = res_data['languages'].split(', ')
year = int(res_data['year'])
duration = res_data['runtimeStr']
brief = res_data['plotLocal'] if res_data['plotLocal'] else res_data['plot']
if res_data['releaseDate']:
showtime = [{res_data['releaseDate']: "发布日期"}]
else:
showtime = None
other_info = {}
other_info['分级'] = res_data['contentRating'] if res_data['contentRating'] else None
other_info['IMDb评分'] = res_data['imDbRating'] if res_data['imDbRating'] else None
other_info['Metacritic评分'] = res_data['metacriticRating'] if res_data['metacriticRating'] else None
other_info['奖项'] = res_data['awards'] if res_data['awards'] else None
raw_img, ext = self.download_image(res_data['image'])
data = {
'title': title,
'orig_title': orig_title,
'other_title': None,
'imdb_code': imdb_code,
'director': director,
'playwright': playwright,
'actor': actor,
'genre': genre,
'showtime': showtime,
'site': None,
'area': area,
'language': language,
'year': year,
'duration': duration,
'season': None,
'episodes': None,
'single_episode_length': None,
'brief': brief,
'is_series': is_series,
'other_info': other_info,
'source_site': self.site_name,
'source_url': effective_url,
}
self.raw_data, self.raw_img, self.img_ext = data, raw_img, ext
return data, raw_img
@classmethod
def get_effective_url(cls, raw_url):
code = cls.regex.findall(raw_url)
if code:
return f"https://www.imdb.com/title/{code[0]}/"
else:
return None
@classmethod
def get_api_url(cls, url):
return f"https://imdb-api.com/zh/API/Title/{IMDB_API_KEY}/{cls.regex.findall(url)[0]}/FullActor,"

View file

@ -1216,7 +1216,7 @@ select::placeholder {
font-weight: lighter;
letter-spacing: 0.1rem;
word-break: keep-all;
opacity: 0.8;
opacity: 1;
position: relative;
top: -1px;
}
@ -1239,6 +1239,13 @@ select::placeholder {
font-weight: bold;
}
.source-label.source-label__imdb {
background-color: #F5C518;
color: #121212;
border: none;
font-weight: bold;
}
.main-section-wrapper {
padding: 32px 48px 32px 36px;
background-color: #f7f7f7;

File diff suppressed because one or more lines are too long

View file

@ -1,10 +1,12 @@
// source label name should match the enum value in `common.models.SourceSiteEnum`
$in-site-color: $color-primary
$douban-color-primary: #319840
$douban-color-secondary: white
$in-site-color: $color-primary
$spotify-color-primary: #1ed760
$spotify-color-secondary: black
$imdb-color-primary: #F5C518
$imdb-color-secondary: #121212
.source-label
display: inline
@ -20,7 +22,7 @@ $spotify-color-secondary: black
font-weight: lighter
letter-spacing: 0.1rem
word-break: keep-all
opacity: 0.8
opacity: 1
position: relative
@ -38,4 +40,9 @@ $spotify-color-secondary: black
background-color: $spotify-color-primary
color: $spotify-color-secondary
border: none
font-weight: bold
font-weight: bold
&.source-label__imdb
background-color: $imdb-color-primary
color: $imdb-color-secondary
border: none
font-weight: bold