Route One - automation for bulletins
 |
| Pretty endpoint page (minimalism) |
After discovering the ease of the command line YouTube downloaders, i set out to create a very quick aggregator for football content which would automatically get audio files ready for Monday mornings Route One Podcast.
Note: this project is in no way endorsed or used by anyone other than me.
First we get the channel file, listing the channels we want to draw from:
with open("channels.json", "r") as f: channels = json.loads(f.read())
Then, for each channel, we download the metadata of the last 80 videos:
for channel in channels:
id = channel["url"]
os.system(f"./yt-dlp -q --progress --skip-download --write-info-json -I 0:80:1 {id} -o 'data/%(id)s'")
Then we gather the data, sorting it and trimming off any irrelevant videos. In this case we measure "relevance" by the metric of comments on the video.
data = []
for f in [file for file in os.listdir("data") if os.path.isfile(f"data/{file}")]:
with open(f"data/{f}", "r") as raw:
file = json.loads(raw.read())
#os.remove(f"data/{f}")
if "duration" in file.keys():
video = {
"id":file["id"],
"title":clean(file["title"]),
"description":clean(file["description"]),
"uploader":file["uploader"],
"views":file["view_count"],
"likes":file["like_count"],
"comments":file["comment_count"] if "comment_count" in file.keys() else 1000
}
data.append(video)
# sort and trim the list of videos
data.sort(key=lambda x: x["comments"]) # sets the variable we sort by
data = data[-10:]
# delete the previously gatered audio files
for f in [file for file in os.listdir("audio") if os.path.isfile(f"audio/{file}")]:
os.remove(f"audio/{f}")
with open(f"data/{f}", "r") as raw:
file = json.loads(raw.read())
#os.remove(f"data/{f}")
if "duration" in file.keys():
video = {
"id":file["id"],
"title":clean(file["title"]),
"description":clean(file["description"]),
"uploader":file["uploader"],
"views":file["view_count"],
"likes":file["like_count"],
"comments":file["comment_count"] if "comment_count" in file.keys() else 1000
}
data.append(video)
# sort and trim the list of videos
data.sort(key=lambda x: x["comments"]) # sets the variable we sort by
data = data[-10:]
# delete the previously gatered audio files
for f in [file for file in os.listdir("audio") if os.path.isfile(f"audio/{file}")]:
os.remove(f"audio/{f}")
We then download the chosen files and update the website where the audio files are available for myself.
for video in data:
os.system(f"./yt-dlp -x --audio-format mp3 {video['id']} -o 'audio/%(id)s'")
#write the index file
with open("index.html", "w") as f:
# get the template file
with open("template.html", "r") as t:
template = t.read()
f.write(template)
for video in data[::-1]:
path = f"audio/{video['id']}.mp3"
f.write(f"""
<div class="container">
<audio controls src='{path}'></audio>
<p class="title"><b>Title:</b> {video['title']}<br><em>@ {video['uploader']}</em></p>
<p><b>Views:</b> {video['views']}</p>
<p><b>Likes:</b> {video['likes']}</p>
<p><b>Comments:</b> {video['comments']}</p>
</div>
""")
f.write("</body></html>")
os.system(f"./yt-dlp -x --audio-format mp3 {video['id']} -o 'audio/%(id)s'")
#write the index file
with open("index.html", "w") as f:
# get the template file
with open("template.html", "r") as t:
template = t.read()
f.write(template)
for video in data[::-1]:
path = f"audio/{video['id']}.mp3"
f.write(f"""
<div class="container">
<audio controls src='{path}'></audio>
<p class="title"><b>Title:</b> {video['title']}<br><em>@ {video['uploader']}</em></p>
<p><b>Views:</b> {video['views']}</p>
<p><b>Likes:</b> {video['likes']}</p>
<p><b>Comments:</b> {video['comments']}</p>
</div>
""")
f.write("</body></html>")
