def analyse_movies_director(movie_director):
dir_lst = []
for movie in movie_director:
for dir in movie['3_movie_director']:
dir_lst.append(dir)
dir1 = list(dict.fromkeys(dir_lst)) #Converting into dict for removing
#duplicates
director_lst = []
for length in range(len(dir1)):
lst = str(length)
lst = []
count = 1
for director in dir_lst:
if director == dir1[length]:
lst.append(count)
count += 1
director_lst.append(len(lst))
#Putting all the data in dictionary
movie_director_dir = {}
for movie_dir in range(len(director_lst)):
movie_director_dir[dir1[movie_dir]] = director_lst[movie_dir]
return movie_director_dir
top_movies = scrape_top_list()
movie_detail_lists = get_movie_list_details(top_movies[:10])
print(analyse_movies_director(movie_detail_lists))
cut_url=cut.replace("/", "")
cut_url_list.append(cut_url)
#Creation of file of name like as tt0066763,tt0345623.
for count in range(len(cut_url_list)):
if os.path.isfile(("Task_9_file/")+cut_url_list[count]):
print("File Exist")
else:
time.sleep(3)
response=requests.get(movie_url[count])
with open(("Task_9_file/")+cut_url_list[count],"w") as file_data:
file_data.write(response.text)
file_data.close()
print("File Created")
scraped_data=scrape_top_list()
scrape_movie_details_with_time(scraped_data)
# #
# import os
# def scrape_movie_details_with_time(movies):
# lis =[]
# movie_url=[]
# cut_url_list=[]
# for movie in movies:
# movie_url.append(movie['5_Url'])
# cut=movie['5_Url'].replace("https://www.imdb.com/title/", "")
time.sleep(1)
response = requests.get(movie_cast_url) # Requests for half links
soup = BeautifulSoup(response.text, 'html.parser')
main_div = soup.find('div', attrs={"class": "article", "id": "titleCast"})
sub_div = main_div.find('div', class_="see-more")
full_link = movie_cast_url + sub_div.a['href'] #Addition of two half links
time.sleep(1)
respons2 = requests.get(
full_link) # Requests for data scrape from full-link
soup = BeautifulSoup(respons2.text, "html.parser")
main_div2 = soup.find('table', class_="cast_list")
td = main_div2.find_all("td", class_="primary_photo")
actor_id = []
actor_name = []
#Scrape Actor Id and Name
my_list = []
my_dict = {"Imdb_Id": "", "Name": ""}
for count in td:
tag_a = count.find('a')
my_dict["Imdb_Id"] = tag_a['href'][6:-1]
my_dict["Name"] = tag_a.img['title']
my_list.append(my_dict)
my_dict = {"Imdb_Id": "", "Name": ""}
return my_list
movie_lst = []
for scraped_data in scrape_top_list():
Movie_name = scraped_data['1_Name']
# pprint(scrape_movie_cast(scraped_data['5_Url']))