name = BeautifulSoup(data.text, "html.parser")
def director_analysis(soup):
genres_movie = []
unique_genres = []
for lan in soup:
genres_movie.append(lan["genres"])
# print(genres_movie)
for i in genres_movie:
if i not in unique_genres:
# for k in i:
if i not in unique_genres:
unique_genres.append(i)
# print(unique_genres)
new_dict = {}
for i in unique_genres:
count = 1
for j in genres_movie:
# for k in j:
if i == j:
count = count + 1
new_dict[i] = count
data = open("saraltask11.json", "w")
saral = json.dumps(new_dict, indent=4)
data.write(saral)
pprint(new_dict)
director_analysis(scrape_movie_details(movie_function(name)))
"1970": [],
"1980": [],
"1990": [],
"2000": [],
"2010": [],
"2020": []
}
for i in task:
if i["movie_year"] >= 1960 and i["movie_year"] <= 1969:
dict_new["1960"].append(i)
elif i["movie_year"] >= 1970 and i["movie_year"] <= 1979:
dict_new["1970"].append(i)
elif i["movie_year"] >= 1980 and i["movie_year"] <= 1989:
dict_new["1980"].append(i)
elif i["movie_year"] >= 1990 and i["movie_year"] <= 1999:
dict_new["1990"].append(i)
elif i["movie_year"] >= 2000 and i["movie_year"] <= 2010:
dict_new["2000"].append(i)
elif i["movie_year"] >= 2010 and i["movie_year"] <= 2019:
dict_new["2010"].append(i)
elif i["movie_year"] >= 2020 and i["movie_year"] <= 2030:
dict_new["2020"].append(i)
pprint(dict_new)
data = open("saraltask3.json", "w")
saral = json.dumps(dict_new, indent=4)
data.write(saral)
pprint(dict_new)
scrape_top_list(movie_function(name))
data = requests.get(url)
name = BeautifulSoup(data.text, "html.parser")
def group_by_year(task):
year = []
unique_year = []
new_list = []
for divs in name.find_all("span", class_='secondaryInfo'):
years = int(divs.text[1:5])
year.append(years)
for i in year:
if i not in unique_year:
unique_year.append(i)
uniques_year = sorted(unique_year)
print(uniques_year)
newlist = []
for i in uniques_year:
newdict = {}
for j in task:
if j["movie_year"] == i:
newdict[i] = j
newlist.append(newdict)
pprint(newlist)
data = open("saraltask2.json", "w")
saral = json.dumps(newlist, indent=4)
data.write(saral)
group_by_year(movie_function(name))
data = requests.get(url)
name = BeautifulSoup(data.text, "html.parser")
def analyse_movies_language(soup):
language_movie = []
unique_language = []
for lan in soup:
language_movie.append(lan["movie_language"])
print(language_movie)
for i in language_movie:
for k in i:
if k not in unique_language:
unique_language.append(k)
print(unique_language)
new_dict = {}
for i in unique_language:
count = 1
for j in language_movie:
for k in j:
if i == k:
count = count + 1
new_dict[i] = count
data = open("saraltask6.json", "w")
saral = json.dumps(new_dict, indent=4)
data.write(saral)
print(new_dict)
analyse_movies_language(scrape_movie_details(movie_function(name)))
list_director=[]
list_language=[]
detail_movie["movie_name"]=i["movie_name"]
names =soup1.find("div", class_="credit_summary_item")
for name in names.find_all("a"):
list_director.append(name.text)
detail_movie["director"]=list_director
for man in soup1.find_all("div", class_="txt-block"):
for mans in man("a"):
j=mans.get("href")
if j=="/search/title?country_of_origin=in" :
detail_movie["movie_country"]=mans.text
elif "/search/title?title_type=feature&primary_language" in j:
list_language.append(mans.text)
detail_movie["movie_language"]=list_language
for runtime in man.find_all("time"):
detail_movie["runtime"]=runtime.text
poster=soup1.find("div", class_="poster")
for links in poster.find_all("img"):
link=links.get("src")
detail_movie["poster_img_url"]=link
for genres in soup1.find_all("div", class_="see-more inline canwrap"):
genres_movie=genres.find("a")
detail_movie["genres"]=genres_movie.text
list_movie.append(detail_movie)
data=open("saraltaskch4.json","w")
saral=json.dumps(list_movie, indent=4)
data.write(saral)
return list_movie
print(scrape_movie_details(movie_function(name)))