Created
November 26, 2019 09:00
-
-
Save psyaro/09e7a467e0a57b76f2d3067b1669a094 to your computer and use it in GitHub Desktop.
youtube_subtitles_collecter
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 time | |
from selenium import webdriver | |
from selenium.webdriver.chrome.options import Options | |
from bs4 import BeautifulSoup | |
from datetime import timedelta | |
import pandas as pd | |
def get(): | |
options = Options() | |
options.add_argument('--headless') | |
options.add_argument('--window-size=1024,768') | |
with webdriver.Chrome(executable_path="xxxxxxxxxxxxxxxxx", chrome_options=options) as d: | |
d.get('https://www.youtube.com/watch?v=2rfVAGzihrg') | |
d.implicitly_wait(2) | |
x = d.find_element_by_xpath("//button[@aria-label='その他の操作']") | |
print(x.get_attribute('outerHTML')) | |
x.click() | |
time.sleep(0.5) | |
x = d.find_element_by_css_selector('ytd-menu-service-item-renderer:nth-child(2)').click() | |
time.sleep(0.5) | |
d.implicitly_wait(2) | |
x = d.page_source | |
return x | |
def main(): | |
x = get() | |
s = BeautifulSoup(x, 'lxml') | |
ans = [] | |
for x in s.select('.cue.style-scope.ytd-transcript-body-renderer'): | |
t = int(x.get('start-offset')) / 1000 | |
dt = timedelta(seconds=t) | |
s = x.string.replace('\n ', '')[2:] | |
print(t, s) | |
ans.append([t, dt, s]) | |
pd.DataFrame(ans).to_csv('temp.csv', index=None) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment