def first():
data = scrape_top_list()
for i in data:
movie_url = i['url']
cast_link = movie_url + 'fullcredits#cast'
linked_Data = link_movie(movie_url, cast_link)
total_data_list.append(linked_Data)
js = json.dumps(total_data_list, indent=4, sort_keys=True)
with open("Total_movie_list_with_casts.json",
"w") as q: # Total movies List of 250 movies
q.write(js)
## In this task, I have counted all the movies that have been released in Hindi, English and Malayalam languages.
from Task5 import get_movie_list_details
from Task1 import scrape_top_list
movies_list = scrape_top_list()
top_ten_movie = movies_list[:250]
def analyse_movies_language(how_many_movies):
allmovies = get_movie_list_details(how_many_movies)
hindi = 0
english = 0
malayalam = 0
for each_movie in allmovies:
# print (allmovies)
lang_list = each_movie['Language']
for i in lang_list:
if i == "Hindi":
hindi += 1
elif i == "English":
english += 1
elif i == "Malayalam":
malayalam+=1
lang_dic = {'Hindi': hindi, 'English': english, 'Malayalam': malayalam}
return (lang_dic)
print (analyse_movies_language(top_ten_movie))
from Task1 import scrape_top_list
import requests
import json
from bs4 import BeautifulSoup
from pprint import pprint
name1 = scrape_top_list()
year = []
def group_by_decade():
i = 0
while i < len(name1):
year.append(name1[i]["year"])
i = i + 1
year.sort()
j = 0
my_dict = {}
while j < len(year):
dec = (year[j] // 10) * 10
k = 0
decade = []
while k < len(name1):
if name1[k]["year"] >= dec and name1[k]["year"] < (dec + 10):
decade.append(name1[k])
my_dict[dec] = decade
k = k + 1
j = j + 1
with open("decade_vise_movie.json", "w") as saral_data3:
json.dump(my_dict, saral_data3, indent=4)
def funfirst():
data1 = scrape_top_list()
for i in data1:
castLink = i['url'] + 'fullcredits#cast'
casting(castLink)
time = soup.find("div",class_="subtext")
runtime = time.find("time").get_text().strip()
hour_in_min = (int(runtime[0])) *60
i = 0
mins = ""
b = (runtime[3:])
while i < len(b):
if b[i] == "m":
break
mins = mins + b[i]
i = i + 1
runtime_of_movie = hour_in_min + int(mins)
movie_genre = time.find_all("a")
movie_genre.pop()
for i in movie_genre:
genre = i.get_text()
gen.append(genre)
details["movie_name"] = name1["name"]
details["director"] = dire
details["country"] = "India"
details["poster_url"] = movie_poster
details["language"] = lang
details["movie_bio"] = movie_bio
details["runtime"] = runtime_of_movie
details["movie_genre"] = gen
list1.append(details.copy())
with open("10movies_details.json","w") as movie:
json.dump(list1,movie,indent=4)
return(list1)
top_movie_list = movies_details(scrape_top_list())