Created
January 16, 2019 06:10
-
-
Save rachmadaniHaryono/96446c5578215c54ab9073399f2f567c to your computer and use it in GitHub Desktop.
parse youtube watch later
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 re | |
import json | |
from bs4 import BeautifulSoup | |
def parse(html_file): | |
"""parse youtube watch later html source. | |
>>> html_file = "youtube_wl.html" | |
>>> parse(html_file) | |
... | |
""" | |
with open(html_file) as f: | |
soup = BeautifulSoup(f.read(), 'html.parser') | |
scs = [ | |
str(x.contents[0]) for x in soup.select('script') | |
if x.contents and 'simpleText' in x.contents[0]] | |
json_match = re.search( | |
r'window\["ytInitialData"\]\s+=\s+.+;', scs[0]) | |
json_s = json_match.group(0).strip().split( | |
'window["ytInitialData"]', 1)[1].split('=', 1)[1].rsplit(';', 1)[0] | |
js_d = json.loads(json_s) | |
# js_d['sidebar']['playlistSidebarRenderer']['items'][0]['playlistSidebarPrimaryInfoRenderer']['stats'] | |
# Out[74]: [{'simpleText': '145 videos'}, {'simpleText': 'Updated today'}] | |
items_stats = ( | |
js_d['sidebar']['playlistSidebarRenderer']['items'][0] | |
['playlistSidebarPrimaryInfoRenderer']['stats'] | |
) | |
items = ( | |
js_d['contents']['twoColumnBrowseResultsRenderer']['tabs'][0] | |
['tabRenderer']['content']['sectionListRenderer']['contents'][0] | |
['itemSectionRenderer']['contents'][0] | |
['playlistVideoListRenderer']['contents'] | |
) | |
video_ids = [x['playlistVideoRenderer']['videoId'] for x in items] | |
return { | |
'json_data': js_d, | |
'stats': items_stats, | |
'items': items, | |
'video_ids': video_ids, | |
} | |
def parse_json(json_file): | |
"""parse youtube watch later json source. | |
>>> html_file = "youtube_wl.json" | |
>>> parse(html_file) | |
... | |
example for json url: | |
https://www.youtube.com/browse_ajax?ctoken=<str>&continuation=<str>&itct=<str> | |
""" | |
with open(json_file) as f: | |
js_d = json.load(f) | |
items = ( | |
js_d[1]['response']['continuationContents'] | |
['playlistVideoListContinuation']['contents'] | |
) | |
video_ids = [x['playlistVideoRenderer']['videoId'] for x in items] | |
return { | |
'json_data': js_d, | |
'items': items, | |
'video_ids': video_ids, | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment