Last active
August 29, 2015 14:23
-
-
Save Radcliffe/4c4cb3cab2598815aacc to your computer and use it in GitHub Desktop.
Find the titles and running times of videos in a YouTube playlist by scraping the web page
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
# Python script to list the titles and running times of the videos | |
# in a YouTube playlist. | |
# Note: Only works for up to 100 videos. TODO: Fix this bug. | |
# The playlist id can be found in the playlist's URL. | |
playlist_id = "PLt5AfwLFPxWLNZRKWlcRmTABh_SExiiCj" | |
from lxml import html | |
import requests | |
url = "https://www.youtube.com/playlist?list=%s" % playlist_id | |
page = requests.get(url) | |
tree = html.fromstring(page.text) | |
body = tree.body | |
items = body.get_element_by_id('pl-load-more-destination') | |
total_seconds = 0 | |
for item in items: | |
try: | |
running_time = item[6][0][0][0].text | |
mm, ss = map(int, running_time.split(':')) | |
total_seconds += 60*mm + ss | |
title = item.get('data-title') | |
print (("%s\t%s" % (running_time, title))) | |
except: | |
pass | |
mm = total_seconds // 60 | |
ss = total_seconds % 60 | |
print '%d:%02d\tTOTAL' % (mm, ss) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment