def analyse_movies_language(movies):
list_1 = []
list_2 = []
dict = {}
for movie in movies:
movie_langauge = movie['langauge']
for lang_1 in movie_langauge:
list_1.append(lang_1)
# print(list_1)
for i in list_1:
if i not in list_2:
list_2.append(i)
for j in list_2:
count = 0
for k in list_1:
if j == k:
count += 1
dict[j] = count
print(dict)
scrap_list = scrap_top_list()[0:30]
# pp(scrape_movie_details(scrap_list))
vishal = scrape_movie_details(scrap_list)
analyse_movies_language(vishal)
# print(scrape_movie_details(scrap_list))
from scraping import scrap_top_list
from pprint import pprint as pp
# pprint.pprint(scrap_top_list())
again_dict = {}
def group_by_decade(movies):
for movie in movies:
if movie['movie_year'][:-1]+'0' not in again_dict:
again_dict[movie['movie_year'][:-1]+'0'] = []
again_dict[movie['movie_year'][:-1]+'0'].append(movie)
pp(again_dict)
group_by_decade(scrap_top_list())
def analyse_movies_directors(movies):
# pp(movies)
list_1 = []
list_2 = []
for director in movies:
# pp(director)
director_1 = director['directer_name']
# pp(director_1)
dict = {}
for i in director_1:
# pp(i)
list_1.append(i)
# pp(list_1)
for j in list_1:
if j not in list_2:
list_2.append(j)
for k in list_2:
count = 0
for l in list_1:
if k == l:
count += 1
dict[k] = count
pp(dict)
scrap_list = scrap_top_list()[0:10]
analyse_movies = scrape_movie_details(scrap_list)
analyse_movies_directors(analyse_movies)
list_of_item = []
for i in movie:
dict_of_item = {}
new_url = i['url_link']
detail = requests.get(new_url)
soup = BeautifulSoup(detail.text, 'html.parser')
movie_rating = soup.find('span', itemprop='ratingValue').text
name = soup.find('div', class_='title_wrapper')
movie_year = name.find('span', id='titleYear').text
movie = name.find('h1').text
movie_name = ""
for i in movie:
if i == "(":
break
else:
movie_name += i
dict_of_item['url'] = new_url
dict_of_item['movie_rating'] = movie_rating
dict_of_item['movie_name'] = movie_name
dict_of_item['movie_year'] = movie_year
list_of_item.append(dict_of_item)
return list_of_item
# pp(list_of_item)
new_link = scrap_top_list()[0:10]
pp(get_movie_list_details(new_link))
import requests,json,os
from bs4 import BeautifulSoup
from pprint import pprint as pp
from scraping import scrap_top_list
from task4 import scrape_movie_details
url = scrap_top_list()[0:5]
# pp(scrape_movie_details(url))
# pp(scrap_top_list())
def scrape_movie_details_1(movies):
# pp(movies)
for movie in movies:
movie_url = movie['poster_image_url']
for url in movie_url:
movie_url_1 = url[7:16]
file_name = movie_url_1 + ".json"
# pp(file_name)
if os.path.isfile(file_name):
with open (file_name,"r") as file:
data = json.load(file)
# pp(data)
else:
file_1 = open(file_name,"w")
json.dump(movie,file_1)
print("succesfully")
url = scrap_top_list()[0:50]
detail_movie = scrape_movie_details(url)
# pp(scrape_movie_details(scrap))
# pp(scrape_movie_cast())
# pp(scrap_top_list())
# print(scrap_top_list())
def get_movie_list_details(movies):
# pp(movies)
main_list = []
for movie in movies:
# pp(movie)
for cast in task_12:
# pp(cast)
movie["Cast"] = cast
# pp(movie)
main_list.append(movie)
with open("task_13.json", "w") as file:
json.dump(main_list, file)
print("succesful")
# return main_list
scrap = scrap_top_list()[0:5]
task_4 = scrape_movie_details(scrap)
task_12 = scrape_movie_cast()
pp(get_movie_list_details(task_4))
# get_movie_list_details(task_4)
# get_movie_list_details(task_12)
from scraping import scrap_top_list
import pprint
from pprint import pprint as pp
# pp(scrap_top_list())
def group_by_year(movies):
# new_dict = {}
new_dict = {}
for movie in movies:
new_list = []
for i in movies:
if movie['movie_year'] == i['movie_year']:
new_list.append(i)
new_dict[movie['movie_year']] = new_list
pprint.pprint(new_dict)
# print(i['o_movie_year'])
group_by_year(scrap_top_list())
# years = []
# for movie in movies:
# if movie['year'] not in years:
# years.append(movie['year'])