alihan/youtube-video-search
1
0
Fork 0
mirror of https://github.com/MoizAhmedd/youtube-video-search.git synced 2021-07-26 20:45:06 +03:00
Code Issues Projects Releases Wiki Activity

random ids

Browse Source
This commit is contained in:
MoizAhmedd
2021-03-19 17:52:35 -04:00
parent 012e00e380
commit b828099d4d
2 changed files with 6 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
app.py
View File

@@ -1,10 +1,10 @@
from flask import Flask, request from flask import Flask, request
from flask_cors import CORS from flask_cors import CORS
import uuid
import subprocess import subprocess
import os import os
app = Flask(__name__) app = Flask(__name__)
CORS(app) CORS(app)
@@ -22,9 +22,10 @@ def index():
def get_mapping(): def get_mapping():
try: try:
video_id = request.args.get('videoid') video_id = request.args.get('videoid')
transcript_id = str(uuid.uuid1())
mapping = {} mapping = {}
rc = subprocess.call(["./get_transcript.sh", video_id]) rc = subprocess.call(["./get_transcript.sh", video_id, transcript_id])
transcript_file = open('transcript.txt','r') transcript_file = open('transcript_{}.txt'.format(transcript_id),'r')
for line in transcript_file.readlines(): for line in transcript_file.readlines():
line_split = line.strip().split(' ') line_split = line.strip().split(' ')
timestamp = line_split[0] timestamp = line_split[0]
@@ -35,7 +36,7 @@ def get_mapping():
mapping[word] = sorted(list(set(mapping[word]))) mapping[word] = sorted(list(set(mapping[word])))
else: else:
mapping[word] = [timeStampSeconds] mapping[word] = [timeStampSeconds]
os.remove('transcript.txt') os.remove('transcript_{}.txt'.format(transcript_id))
return {'mapping':mapping} return {'mapping':mapping}
except: except:
return {'mapping':{}} return {'mapping':{}}

2
get_transcript.sh
View File

@@ -8,7 +8,7 @@ youtube-dl --skip-download --write-auto-sub "https://www.youtube.com/watch?v=$1"
vtt=$(ls *.vtt) vtt=$(ls *.vtt)
# Extract the subs and save as plaintext, removing time, new lines and other markup # Extract the subs and save as plaintext, removing time, new lines and other markup
sed '1,/^$/d' "$vtt" | sed 's/<[^>]*>//g' | awk -F. 'NR%8==1{printf"%s ",$1}NR%8==3' > "transcript.txt" sed '1,/^$/d' "$vtt" | sed 's/<[^>]*>//g' | awk -F. 'NR%8==1{printf"%s ",$1}NR%8==3' > "transcript_$2.txt"
# Remove the original .vtt subs file # Remove the original .vtt subs file
rm -f "$vtt" rm -f "$vtt"