Youtube data api v3 playlist keyword generator POC. WIP

search.py

#!/usr/bin/python

###########################################
# Don't forget to pip install --upgrade google-api-python-clien
#
### USAGE: python search.py --q beatles ###
###########################################

import json

from apiclient.discovery import build
from apiclient.errors import HttpError
from oauth2client.tools import argparser


# Set DEVELOPER_KEY to the API key value from the APIs & auth > Registered apps
# tab of
#   https://cloud.google.com/console
# Please ensure that you have enabled the YouTube Data API for your project.
DEVELOPER_KEY = "<YOUR-DEVELOPER-KEY-HERE>"
YOUTUBE_API_SERVICE_NAME = "youtube"
YOUTUBE_API_VERSION = "v3"


def main(args):
    youtube = build(YOUTUBE_API_SERVICE_NAME, YOUTUBE_API_VERSION,
                    developerKey=DEVELOPER_KEY)
    playlists = playlist_search(youtube, args)

    videosMap = {}
    for p in playlists:
        items_map = playlist_items_list_by_playlist_id(youtube,
                                                       part='snippet,contentDetails',
                                                       maxResults=25,
                                                       playlistId=p['id'])

        for element in items_map:
            if element['id'] in videosMap:
                videosMap[element['id']]['occurence'] += 1
            else:
                videosMap[element['id']] = {
                    'title': element['title'],
                    'occurence': 1
                }
    videosMap = sorted(videosMap.items(),
                       key=lambda k_v: k_v[1]['occurence'], reverse=False)
    print(json.dumps(videosMap, indent=4))


def playlist_search(client, options):
    # Call the search.list method to retrieve results matching the specified
    # query term.
    search_response = client.search().list(
        q=options.q,
        part="id,snippet",
        type='playlist',
        order='viewCount',
        # order='relevance',
        maxResults=options.max_results
    ).execute()

    playlists = []

    # Add each result to the appropriate list, and then display the lists of
    # matching videos, channels, and playlists.
    for search_result in search_response.get("items", []):
        playlists.append(
            {
                'id': search_result["id"]["playlistId"],
                'title': search_result["snippet"]["title"]
            })
    # for p in playlists:
    #     print(
    #         'https://www.youtube.com/playlist?list={} {}'.format(p['id'], p['title']))
    return playlists


def playlist_items_list_by_playlist_id(client, **kwargs):
    # See full sample for function
    kwargs = remove_empty_kwargs(**kwargs)

    response = client.playlistItems().list(
        **kwargs
    ).execute()

    videoIdsTitles = []
    items = response['items']
    for i in items:
        videoIdsTitles.append(
            {
                'id': 'https://www.youtube.com/watch?v={}'.format(i['contentDetails']['videoId']),
                'title': i['snippet']['title']
            }
        )

    # print(json.dumps(videoIdsTitles, indent=4))
    return videoIdsTitles


def remove_empty_kwargs(**kwargs):
    good_kwargs = {}
    if kwargs is not None:
        for key, value in kwargs.items():
            if value:
                good_kwargs[key] = value
    return good_kwargs


if __name__ == "__main__":
    argparser.add_argument("--q", help="Search term",
                           default="CC5ca6Hsb2Q")
    argparser.add_argument("--max-results", help="Max results", default=25)
    args = argparser.parse_args()

    try:
        main(args)
    except HttpError as e:
        print("An HTTP error %d occurred:\n%s" % (e.resp.status, e.content))