Commit ·
73db5a0
1
Parent(s): 4563355
Create average_duration.py
Browse filesFile for average duration function.
- average_duration.py +156 -0
average_duration.py
ADDED
|
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#import pyyoutube
|
| 2 |
+
from datetime import timedelta
|
| 3 |
+
#from pyyoutube import playlist
|
| 4 |
+
import re
|
| 5 |
+
import gradio as gr
|
| 6 |
+
from urllib.parse import urlparse, parse_qs
|
| 7 |
+
from contextlib import suppress
|
| 8 |
+
|
| 9 |
+
api_key = "AIzaSyDThR6EJnLkH56c6CpxY7HUZ_bMn4NCAKU"
|
| 10 |
+
import googleapiclient
|
| 11 |
+
from googleapiclient.discovery import build
|
| 12 |
+
from googleapiclient.errors import HttpError
|
| 13 |
+
import datetime
|
| 14 |
+
youtube = build('youtube', 'v3', developerKey=api_key)
|
| 15 |
+
|
| 16 |
+
def playlist_average_duration_func(youtubelink,videoid=False):
|
| 17 |
+
|
| 18 |
+
def playlist_exist_check(playlistlink):
|
| 19 |
+
|
| 20 |
+
def extract_playlist_id(playlistlink):
|
| 21 |
+
match = re.search(r'list=([^&]+)', playlistlink) #It searches for the string 'list=' followed by >=1 characters that are not '&'.
|
| 22 |
+
if match:
|
| 23 |
+
return match.group(1)
|
| 24 |
+
return None
|
| 25 |
+
|
| 26 |
+
playlist_id = extract_playlist_id(playlistlink)
|
| 27 |
+
|
| 28 |
+
if playlist_id is None:
|
| 29 |
+
return False
|
| 30 |
+
|
| 31 |
+
search_request = youtube.playlists().list(
|
| 32 |
+
|
| 33 |
+
part='id',
|
| 34 |
+
id=playlist_id,
|
| 35 |
+
maxResults=1
|
| 36 |
+
)
|
| 37 |
+
|
| 38 |
+
search_response = search_request.execute()
|
| 39 |
+
if 'items' in search_response:
|
| 40 |
+
try:
|
| 41 |
+
playlistdict = search_response['items'][0]
|
| 42 |
+
print("ID of playlist is:- ",playlistdict['id'])
|
| 43 |
+
return playlistdict['id']
|
| 44 |
+
except:
|
| 45 |
+
#print("Video not found.")
|
| 46 |
+
return False
|
| 47 |
+
|
| 48 |
+
playlistid = playlist_exist_check(youtubelink)
|
| 49 |
+
if playlistid == False or playlistid==None:
|
| 50 |
+
print("Playlist doesn't exist")
|
| 51 |
+
return False
|
| 52 |
+
print("1st check passed - Playlist link is valid")
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
#This section retrieves the video ids of all the videos in the playlist, and stores them in a list. 50 in one iteration.
|
| 58 |
+
|
| 59 |
+
vid_ids = []
|
| 60 |
+
next_page_token = None
|
| 61 |
+
while True:
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
pl_request = youtube.playlistItems().list(
|
| 65 |
+
part="contentDetails,snippet",
|
| 66 |
+
playlistId=playlistid,
|
| 67 |
+
maxResults=50, #This is the max limit of videos that can be fetched in one go form a playlist as youtube data v3 API results are paginated
|
| 68 |
+
pageToken=next_page_token
|
| 69 |
+
)
|
| 70 |
+
pl_response = pl_request.execute()
|
| 71 |
+
# print("Reponse obtained from youtube")
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
for item in pl_response['items']:
|
| 76 |
+
vid_id = item['contentDetails']['videoId']
|
| 77 |
+
vid_ids.append(vid_id)
|
| 78 |
+
if videoid==True:
|
| 79 |
+
print(item['contentDetails']['videoId'])
|
| 80 |
+
|
| 81 |
+
next_page_token = pl_response.get("nextPageToken")
|
| 82 |
+
if not next_page_token:
|
| 83 |
+
break
|
| 84 |
+
print("2nd check passed - Playlist read")
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
#This section obtains the playlist name from the playlist id
|
| 89 |
+
pl_request = youtube.playlists().list(
|
| 90 |
+
part="snippet",
|
| 91 |
+
id=playlistid,
|
| 92 |
+
maxResults=1
|
| 93 |
+
)
|
| 94 |
+
pl_response = pl_request.execute()
|
| 95 |
+
playlist = pl_response['items'][0]
|
| 96 |
+
title = playlist['snippet']['title']
|
| 97 |
+
print("Playlist Title:", title)
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
# title = playlist['snippet']['title']
|
| 105 |
+
# print("Playlist Title:", title)
|
| 106 |
+
#This section retrieves the duration of each video in the playlist, and stores them in a list. 50 in one iteration
|
| 107 |
+
|
| 108 |
+
|
| 109 |
+
iterations = len(vid_ids)//50+1
|
| 110 |
+
duration_list = []
|
| 111 |
+
for i in range(iterations):
|
| 112 |
+
start_index = i * 50
|
| 113 |
+
end_index = (i + 1) * 50
|
| 114 |
+
batch_ids = vid_ids[start_index:end_index]
|
| 115 |
+
vid_request = youtube.videos().list(
|
| 116 |
+
part="contentDetails",
|
| 117 |
+
id=','.join(batch_ids)
|
| 118 |
+
)
|
| 119 |
+
|
| 120 |
+
vid_response = vid_request.execute()
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
for item in vid_response['items']:
|
| 124 |
+
duration = item['contentDetails']['duration']
|
| 125 |
+
duration = duration[2:]
|
| 126 |
+
hours = 0
|
| 127 |
+
minutes = 0
|
| 128 |
+
seconds = 0
|
| 129 |
+
|
| 130 |
+
if "H" in duration:
|
| 131 |
+
hours_index = duration.index("H")
|
| 132 |
+
hours = int(duration[:hours_index])
|
| 133 |
+
duration = duration[hours_index+1:]
|
| 134 |
+
|
| 135 |
+
if "M" in duration:
|
| 136 |
+
minutes_index = duration.index("M")
|
| 137 |
+
minutes = int(duration[:minutes_index])
|
| 138 |
+
duration = duration[minutes_index+1:]
|
| 139 |
+
|
| 140 |
+
if "S" in duration:
|
| 141 |
+
seconds_index = duration.index("S")
|
| 142 |
+
seconds = int(duration[:seconds_index])
|
| 143 |
+
|
| 144 |
+
duration = timedelta(hours=hours, minutes=minutes, seconds=seconds)
|
| 145 |
+
duration_list.append(duration)
|
| 146 |
+
print("3rd check passed - Individual video duration calculated")
|
| 147 |
+
total_duration = sum(duration_list, timedelta())
|
| 148 |
+
#Find the average duration of each video in the playlist
|
| 149 |
+
average_duration = total_duration/len(vid_ids)
|
| 150 |
+
print("Total duration of playlist is:- ",total_duration)
|
| 151 |
+
print("Total no. of videos is = ",len(vid_ids))
|
| 152 |
+
print("Average duration of each video is:- ",average_duration)
|
| 153 |
+
#Convert the average suration into HH:MM:SS format
|
| 154 |
+
# average_duration_format = s
|
| 155 |
+
return str(average_duration)
|
| 156 |
+
|