andkamau
/ youtube_screen_scrape.py
Created
October 16, 2016 18:38
— forked from ljmccarthy/youtube_screen_scrape.py
An example of how to download metadata for all videos of a specified YouTube channel using simple BeautifulSoup screen scraping. The data will be much more up-to-date and reliable than the RSS feed or YouTube API results (which is a sad state of affairs really).
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 urllib | |
| import json | |
| from bs4 import BeautifulSoup | |
| from collections import namedtuple | |
| Video = namedtuple("Video", "video_id title duration views thumbnail") | |
| def parse_video_div(div): | |
| video_id = div.get("data-context-item-id", "") | |
| title = div.find("a", "yt-uix-tile-link").text |
andkamau
/ ckan_upload.py
Last active
December 6, 2016 16:09
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 os, sys | |
| from datetime import datetime | |
| from ckanapi import RemoteCKAN | |
| API_KEY = os.getenv("CKAN_API_KEY", None) | |
| USER_AGENT = "openafrica-client" | |
| URL = "https://africaopendata.org" | |
| def upload_files(directory, dataset): |