61 lines
1.2 KiB
Python
61 lines
1.2 KiB
Python
from imdb import IMDb
|
|
import requests
|
|
from bs4 import BeautifulSoup
|
|
import re
|
|
|
|
|
|
def get_movie(imdb_id):
|
|
ia = IMDb()
|
|
|
|
movie = ia.get_movie(imdb_id)
|
|
|
|
return movie
|
|
|
|
|
|
def get_movie_keywords(imdb_id):
|
|
ia = IMDb()
|
|
|
|
movie = ia.get_movie(imdb_id, info="keywords")
|
|
|
|
return movie
|
|
|
|
|
|
def get_api_keyword_count(keyword):
|
|
ia = IMDb()
|
|
|
|
count = len(ia.get_keyword(keyword))
|
|
|
|
return count
|
|
|
|
|
|
def get_website_keyword_count(keyword):
|
|
try:
|
|
page = requests.get("https://www.imdb.com/search/keyword/?keywords=" + keyword)
|
|
except ConnectionError:
|
|
raise
|
|
|
|
soup = BeautifulSoup(page.content, 'html.parser')
|
|
elements = soup.findAll("div", class_="desc")
|
|
|
|
pagination_label = elements[0].text.replace("\n", "")
|
|
|
|
pagination_label_reg = "(\d+,?\d*) titles"
|
|
pattern_match = re.compile(pagination_label_reg).search(pagination_label)
|
|
|
|
if pattern_match is not None:
|
|
return int(pattern_match.group(1).replace(',', ''))
|
|
else:
|
|
return 1
|
|
|
|
|
|
def get_keyword_count(keyword):
|
|
count = get_api_keyword_count(keyword)
|
|
|
|
if count == 50:
|
|
try:
|
|
count = get_website_keyword_count(keyword)
|
|
except Exception as e:
|
|
raise
|
|
|
|
return count
|