def movie_detail_list():
list1 = []
top_movies = scrape_top_list()
for i in top_movies:
link = (i["url"])
data = get_movie_list_details(link)
list1.append(data)
return (list1)
def cach():
movies = scrape_top_list()
all_data = []
for i in movies:
url = i["Url"][-9:]
with open(url + ".json", "r") as file:
data = json.load(file)
j_url = url + ".json"
if not (os.path.exists(j_url)):
print("hi")
url2 = "https://www.imdb.com/title/" + url + "/fullcredits?ref_=tt_cl_sm#cast"
data["cast"] = actores(url2)
with open(j_url, "w+") as file:
d_data = json.dumps(data)
file.write(d_data)
all_data.append(data)
return all_data
def analyse_movies_genre():
url = scrape_top_list()
dict1 = {}
list1 = []
all_data = []
for i in url:
u = (i['url'][-9:-1]) + ".json"
if os.path.exists(u):
with open(u, 'r+') as folder:
data = json.load(folder)
list1.append(data['Genres'][0])
all_data.append(data)
list2 = []
for j in list1:
if j not in list2:
list2.append(j)
for x in list2:
print(x)
count = 0
for t in all_data:
if x in t['Genres']:
count += 1
dict1[x] = count
return (dict1)
from web1 import scrape_top_list
import os,json
from pprint import pprint
from web4 import get_movie_list_details
# import time
# import random
url=scrape_top_list()
for i in url:
u=(i['url'][-9:-1])+".json"
with open(u,'r+') as folder:
data = json.load(folder)
dic={}
for j in data['cast']:
if j['name'] not in data:
dic[j['name']]=1
else:
dic[j['name']]+=1
pprint(dic)
import os, json, time, random
from web1 import scrape_top_list
from web4 import scrape_movie_details
movies = scrape_top_list()
for i in movies:
# time.sleep(random.randint(5,10))
url = i["Url"][-9:] + ".json"
if not (os.path.exists(url)):
all_movies = scrape_movie_details(i["Url"])
with open(url, "w") as file:
data = json.dumps(all_movies)
file.write(data)
print("nahi thi")
else:
print("hai")