Created
October 25, 2021 23:27
-
-
Save eevmanu/3ad125e3c8420dd1784c4211313cfca9 to your computer and use it in GitHub Desktop.
Youtube video stats - get number of views, published date and duration of a video
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import sys | |
import datetime | |
import argparse | |
import urllib.request | |
parser = argparse.ArgumentParser() | |
parser.add_argument('yt_video_url', type=str) | |
args = parser.parse_args() | |
yt_video_url = args.yt_video_url | |
url_prefix = "https://www.youtube.com/watch?v=" | |
if yt_video_url.find(url_prefix) == -1: | |
yt_video_url = url_prefix + yt_video_url | |
with urllib.request.urlopen(yt_video_url) as u: | |
content = str(u.read(), 'utf-8') | |
# <meta itemprop="interactionCount" content="395882"> | |
pattern = "itemprop=\"interactionCount\" content=\"" | |
pos_start = content.find(pattern) | |
if pos_start == -1: | |
sys.exit() | |
pos_start = pos_start + len(pattern) | |
pos_end = content.find("\"", pos_start) | |
if pos_end == -1: | |
sys.exit() | |
yt_video_views = int(content[pos_start : pos_end]) | |
# <meta itemprop="datePublished" content="2020-04-20"> | |
pattern = "itemprop=\"datePublished\" content=\"" | |
pos_start = content.find(pattern) | |
if pos_start == -1: | |
sys.exit() | |
pos_start = pos_start + len(pattern) | |
pos_end = content.find("\"", pos_start) | |
if pos_end == -1: | |
sys.exit() | |
yt_video_published_date = content[pos_start : pos_end] | |
# "lengthSeconds":"45585" | |
pattern = "\"lengthSeconds\":\"" | |
pos_start = content.find(pattern) | |
if pos_start == -1: | |
sys.exit() | |
pos_start = pos_start + len(pattern) | |
pos_end = content.find("\"", pos_start) | |
if pos_end == -1: | |
sys.exit() | |
yt_video_duration = int(content[pos_start : pos_end]) | |
yt_video_duration = str(datetime.timedelta(seconds=yt_video_duration)) | |
print(f"{yt_video_views!r} | {yt_video_published_date!s} | {yt_video_duration!s}") | |
if __name__ == '__main__': | |
pass |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment