Created
May 7, 2015 19:11
-
-
Save iKlotho/f4addb33602bbd28cfdd to your computer and use it in GitHub Desktop.
Youtube annotations Scraper
This file contains 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
import requests | |
from bs4 import BeautifulSoup | |
# set userid to youtube channel id | |
# script will get all the annotations from user's videos | |
url = 'https://www.youtube.com/user/USERID/videos/browse_ajax?action_continuation=1&continuation=4qmFsgI8EhhVQ0VrOTBTOGl1SHQwZVV6Yks4TmtwX2caIEVnWjJhV1JsYjNNZ0FEQUJPQUZnQVdvQWVnRXl1QUVB' | |
r = requests.get(url) | |
soup = BeautifulSoup(r.text) | |
lists = [] | |
bas = 'https://www.youtube.com' | |
for link in soup.find_all('h3','yt-lockup-title'): | |
lists.append(link.a.get('href')) | |
get = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=' | |
for list in lists: | |
gets = get + list[9:] | |
r = requests.get(gets).text | |
soup = BeautifulSoup(r) | |
try: | |
for i in soup.find_all('text'): | |
print i.text | |
except: | |
pass | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment