imdb_scraping/task13.py at main · RajuSonwani/imdb_scraping · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
import os,json,requests,time,random,task1,task12
from bs4 import BeautifulSoup
from pprint import pprint

def movie_detailsLst(movies,cast):
	movie_details_list=[]
	for movie in movies:
		link0=movie["link"]
		movieId=link0[-10:-1]
		# tempDict={}
		if os.path.exists("/home/navgurukul/Desktop/rAju/data/task0/"+link0[-10:-1]+".json"):
			with open("/home/navgurukul/Desktop/rAju/data/task0/"+link0[-10:-1]+".json") as file:
				# tempDict["cast"]=cast[movieId]
				# movie_details_list.append(json.loads(file.read()))
				# movie_details_list.append(tempDict)
				dict0=json.loads(file.read())
				dict0["cast"]=cast[movieId]
				movie_details_list.append(dict0)


		# else:
			# import time
			# time.sleep(random.randint(1,3))
			# page=requests.get(link0).text

			# # data0=file.read()
			# genre_lst=[]
			# director_lst=[]

			# data=BeautifulSoup(page,"html.parser")
			# name=data.find(class_="title_wrapper").h1.text
			# timeClass=data.find(class_="title_wrapper")
			# time=(timeClass.find(class_="subtext").time.text).strip()
			# genre_class=timeClass.find(class_="subtext")
			# genre_a=genre_class.find_all("a")
			# for i in range(len(genre_a)-1):
			# 	genre_lst.append(genre_a[i].text)

			# bio=data.find(class_="summary_text").text
			# director_class=data.find(class_="credit_summary_item")
			# director_a=director_class.find_all("a")
			# for i in range(len(director_a)):
			# 	director_lst.append(director_a[i].text)
			# link=data.find(class_="poster").img["src"]
			# exta_details=data.find("div",attrs={"class":"article","id":"titleDetails"})
			# txt_div=exta_details.find_all("div",class_="txt-block")
			# count=0
			# for div in txt_div:
			# 	if count==2:
			# 		break

			# 	elif div.h4.text== "Country:":
			# 		country_all= div.find_all("a")
			# 		country=[a.text for a in country_all]
			# 		count+=1
			# 	elif div.h4.text=="Language:":
			# 		language_all=div.find_all("a")
			# 		language=[a.text for a in language_all]
			# 		count+=1

			# s={}
			# s["name"]=name[:-8]
			# s["country"]="india"
			# s["genre"]=genre_lst
			# if len(time)==2:
			# 	s["running_time"]=int(time[0])*60
			# else:
			# 	s["running_time"]=int(time[0])*60+int(time[3])
			# s["minfo"]=bio.strip()
			# s["director"]=director_lst
			# s["poster_link"]=link
			# s["language"]=language
			# s["country"]=country
			# movie_details_list.append(json.dumps(s))
			# with open("/home/navgurukul/Desktop/rAju/data/task0/"+link0[-10:-1]+".json","w") as file:
			# 	file.write(json.dumps(s))
	return movie_details_list

	# else:
	# 	data0=requests.get(link).text
	# 	with open("/home/navgurukul/Desktop/rAju/data/aanand.json","w") as file:
	# 		file.write(data0)


# moviesLst=task1.top_250movies()
# cast=task12.movie_Cast(moviesLst)
# pprint(movie_detailsLst(moviesLst,cast))