Lookimi commited on
Commit
90323cf
1 Parent(s): fc09dbe

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -17
app.py CHANGED
@@ -1,17 +1,5 @@
1
 
2
- #
3
 
4
- Fix these riot errors:
5
-
6
- Remove the unused keyword argument in Interface:
7
- gr.Interface(fn=transcript_extract, inputs="textbox", outputs="textbox").launch(share=True)
8
-
9
- Specify the expected number of arguments for the function "transcript_extract":
10
- warnings.warn(Expected 0 arguments for function <function transcript_extract at 0x7f3e82e2b280>, received 0)
11
-
12
- Remove the "share" argument when launching in Spaces:
13
- gr.Interface(fn=transcript_extract, inputs="textbox", outputs="textbox").launch()
14
- #changing the code to have a Gradio Blocks App Menu on Huggingface Space prompting the channel URL
15
  #importing the necessary modules
16
  import os
17
  import urllib.request
@@ -28,10 +16,10 @@ def transcript_extract():
28
  page = urllib.request.urlopen(channel_url)
29
 
30
  #reading the source code
31
- data = page.read()
32
 
33
  #creating a directory to save the transcripts
34
- os.mkdir('Transcripts')
35
 
36
  #finding the transcripts
37
  transcript_links = re.findall(r'(\/watch\?v=[A-Za-z0-9_.-]*)', str(data))
@@ -42,7 +30,7 @@ def transcript_extract():
42
  #access the video page
43
  video_page = urllib.request.urlopen(video_url)
44
  #read the source code
45
- video_data = video_page.read()
46
  #find the transcript
47
  transcript_link = re.findall(r'(\/timedtext_editor\?[A-Za-z0-9_.-]*)', str(video_data))
48
  #check if there is a transcript available
@@ -50,7 +38,7 @@ def transcript_extract():
50
  #access the transcript page
51
  transcript_url ='http://www.youtube.com'+ transcript_link[0]
52
  transcript_page = urllib.request.urlopen(transcript_url)
53
- transcript_data = transcript_page.read()
54
  #find the link to the transcript
55
  transcript_download_link = re.findall(r'(\/api\/timedtext\?[A-Za-z0-9_.-]*)', str(transcript_data))
56
  #check if the transcript is available for download
@@ -67,4 +55,4 @@ def transcript_extract():
67
  print("Transcript not available for video " + link[9:])
68
 
69
  #upload to Huggingface Space
70
- gr.Interface(fn=transcript_extract, inputs="textbox", outputs="textbox", force_reload=True).launch(share=True)
 
1
 
 
2
 
 
 
 
 
 
 
 
 
 
 
 
3
  #importing the necessary modules
4
  import os
5
  import urllib.request
 
16
  page = urllib.request.urlopen(channel_url)
17
 
18
  #reading the source code
19
+ data = page.read().decode("utf-8")
20
 
21
  #creating a directory to save the transcripts
22
+ os.makedirs('Transcripts',exist_ok=True)
23
 
24
  #finding the transcripts
25
  transcript_links = re.findall(r'(\/watch\?v=[A-Za-z0-9_.-]*)', str(data))
 
30
  #access the video page
31
  video_page = urllib.request.urlopen(video_url)
32
  #read the source code
33
+ video_data = video_page.read().decode("utf-8")
34
  #find the transcript
35
  transcript_link = re.findall(r'(\/timedtext_editor\?[A-Za-z0-9_.-]*)', str(video_data))
36
  #check if there is a transcript available
 
38
  #access the transcript page
39
  transcript_url ='http://www.youtube.com'+ transcript_link[0]
40
  transcript_page = urllib.request.urlopen(transcript_url)
41
+ transcript_data = transcript_page.read().decode("utf-8")
42
  #find the link to the transcript
43
  transcript_download_link = re.findall(r'(\/api\/timedtext\?[A-Za-z0-9_.-]*)', str(transcript_data))
44
  #check if the transcript is available for download
 
55
  print("Transcript not available for video " + link[9:])
56
 
57
  #upload to Huggingface Space
58
+ gr.Interface(fn=transcript_extract, inputs="textbox", outputs="textbox").launch(share=True)