-
Notifications
You must be signed in to change notification settings - Fork 0
/
Extract_func.py
207 lines (153 loc) · 8.69 KB
/
Extract_func.py
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
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
#-----------------------------------------------------------------------------------------------------------------------------------------------------
import streamlit as st
#============================================= Getting the youtube channel data =====================================================
def get_channel_data(youtube,channel_id):
data_requested = []
request = youtube.channels().list(
part="snippet,contentDetails,statistics,status",
id=",".join(channel_id))
response = request.execute()
res_coun =len(response)
for item in response.get("items", []):
data = dict(
_id=item["id"],
channel_name=item["snippet"]["title"],
channel_id=item["id"],
subscriberCount=item["statistics"]["subscriberCount"],
videoCount=item["statistics"]["videoCount"],
channel_Description=item["snippet"]["description"],
playlist_id=item["contentDetails"]["relatedPlaylists"]["uploads"],
channel_status=item["status"]["privacyStatus"],
viewCount=item["statistics"]["viewCount"])
data_requested.append(data)
return data_requested
# calling the function
#a = get_channel_data(youtube,channel_id)
# calling the function
#channel_data = get_channel_data(youtube,channel_id)
#channel_data
#========================================================== Getting the playlist infomation ======================================================
def get_playlist_info(youtube,channel_data):
playlist = []
a1=[]
# looping through each list
for i in channel_data:
# getting the playlist value using the key to get playlist id
channelid = i["_id"]
request = youtube.playlists().list(
part="snippet,contentDetails",
channelId=channelid,
maxResults=50)
response = request.execute()
playlist_ids = []
for i in response["items"]:
playlist_data = dict ( channel_id = i["snippet"]["channelId"],
playlist_id =i["id"],
playlist_name = i["snippet"]["title"],
)
playlist_ids.append(playlist_data)
#print(playlist_data)
a1.append(playlist_data)
playlist_data = dict(_id =channelid,playlists =playlist_ids)
playlist.append(playlist_ids )
return a1
#play_list = get_playlist_info(youtube,channel_data)
#======================================================== Getting the vedio ids ==============================================================
def playlist_video_list(youtube,channel_id):
play_vedio = []
for channel_ids in channel_id:
playlist_request = youtube.playlists().list( part="snippet,contentDetails",channelId=channel_ids,maxResults=50)
playlist_response=playlist_request.execute()
play_lists = []
next_page_token = playlist_response.get("nextPageToken")
Pages = True
for ids in playlist_response["items"]:
play_lists.append(ids["id"])
while Pages:
if next_page_token is None:
Pages = False
else:
playlist_request = youtube.playlists().list( part="snippet,contentDetails",channelId=",".join(channel_id),maxResults=50)
playlist_response=playlist_request.execute()
for ids in playlist_response["items"]:
play_lists.append(ids["id"])
next_page_token = playlist_response.get("nextPageToken")
# looping the playlist ids from the list
for playlist_IDS in play_lists:
vedio_id_request = youtube.playlistItems().list(part = "snippet,contentDetails", playlistId= playlist_IDS,maxResults=50)
vedio_id_response = vedio_id_request.execute()
vedio_page_token = vedio_id_response.get("nextPageToken")
vedio_Pages =True
for i in vedio_id_response["items"]:
data = dict(vedio_id = i["snippet"]["resourceId"]["videoId"],
playlist = i["snippet"]["playlistId"],
channel_id = i["snippet"]["channelId"])
play_vedio.append(data)
while vedio_Pages:
if vedio_page_token is None:
vedio_Pages = False
else:
vedio_id_request = youtube.playlistItems().list(part = "snippet,contentDetails", playlistId= playlist_IDS,maxResults=50)
vedio_id_response = vedio_id_request.execute()
for i in vedio_id_response["items"]:
data = dict(vedio_id = i["snippet"]["resourceId"]["videoId"],
playlist = i["snippet"]["playlistId"],
channel_id = i["snippet"]["channelId"])
play_vedio.append(data)
vedio_page_token = vedio_id_response.get("nextPageToken")
#print(play_lists)
return play_vedio
#out = playlist_vedio_list(youtube,channel_id)
# ========================================================== Getting the vedio contents ========================================================
def get_video_contents(youtube,out):
import isodate
vedio_contents = []
a =[]
for ids in out:
playlist_id = ids.get("playlist")
vedio_id = ids.get("vedio_id")
channel_id =ids.get("channel_id")
request = youtube.videos().list(part="snippet,statistics,contentDetails",id=vedio_id)
response = request.execute()
#print(response["items"])
for i in range(len(response["items"])):
channel_id = dict (Channel_id = response["items"][i]["snippet"]["channelId"])
c = response["items"][i]["snippet"]["channelId"]
#print(c)
L1 = []
vedio_time = isodate.parse_duration(response["items"][i]["contentDetails"]["duration"])
vedio_data = dict(Channel_id = response["items"][i]["snippet"]["channelId"],
video_id =response["items"][i]["id"],
playlist_id = playlist_id,
video_name = response["items"][i]["snippet"]["title"],
published_data = response["items"][i]["snippet"]["publishedAt"],
view_count = response["items"][i]["statistics"].get("viewCount",0),
Likes_count = response["items"][i]["statistics"].get("likeCount",0),
Dislikes_count = response["items"][i]["statistics"].get("dislikeCount",0),
favorite_count = response["items"][i]["statistics"].get("favoriteCount",0),
Comment_count = response["items"][i]["statistics"].get("commentCount",0),
duration =vedio_time.total_seconds(),
Description=response["items"][i]["snippet"]["description"])
vedio_contents.append(vedio_data)
#print(vedio_contents)
return vedio_contents
#vedio_cont = vedio_contents(youtube,out)
# ====================================================== Getting the Comments for each vedio =======================================
def get_comments(youtube,out):
comments = []
for ids in out:
vedio_id = ids.get("vedio_id")
request = youtube.commentThreads().list(part="snippet,replies", videoId=vedio_id,maxResults=100)
response = request.execute()
for i in response["items"]:
data = dict(channel_id = i['snippet']["channelId"],
comment_id = i['id'],
video_id = i['snippet']["videoId"],
comment_author= i['snippet']['topLevelComment']['snippet'].get('authorDisplayName',None),
comment_published =i['snippet']['topLevelComment']['snippet'].get("publishedAt",None),
comment_text = i['snippet']['topLevelComment']['snippet'].get('textOriginal',None))
comments.append(data)
#print(data)
return comments
#video_comm = get_comments(youtube,out)
#----------------------------------------------------------------------------------------------------------------------------------------------------