Forked from igorbrigadir/scrape-storify-stories.py
Last active
December 28, 2017 22:47
-
-
Save vitorio/be7919835f54c290957b4bb97ee8bd7b to your computer and use it in GitHub Desktop.
Download all Storify stories for a given user
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
#!/usr/bin/python | |
try: | |
import simplejson as json | |
except: | |
import json | |
import requests | |
import math | |
import sys | |
import argparse as ap | |
import sys | |
import os | |
parser = ap.ArgumentParser(description='Downloads storifyuser.json to current directory & all Storify collections to storifyuser/storify-slug.json') | |
parser.add_argument('STORIFY_SCREEN_NAME', nargs='?') | |
args = parser.parse_args() | |
if args.STORIFY_SCREEN_NAME is None: | |
print('usage: python scrape-storify-stories.py <storify_screen_name>') | |
sys.exit(2) | |
target_user = args.STORIFY_SCREEN_NAME | |
print('Processing', target_user) | |
STORIFY_API_KEY = '' # Your Storify API Key: http://dev.storify.com/request | |
API_URL = 'https://api.storify.com/v1' | |
# eg: https://api.storify.com/v1/users/reportedly?&api_key=... | |
endpoint = "{0}/{1}/{2}?api_key={3}".format(API_URL, 'users', target_user, STORIFY_API_KEY) | |
user_json = requests.get(endpoint).json() | |
with open("{0}.json".format(target_user), 'w') as f: | |
json.dump(user_json, f) | |
number_of_stories = user_json['content']['stats']['stories'] | |
stories = list() | |
pages = int(math.ceil(number_of_stories / 50))+1 | |
print (target_user, 'has', number_of_stories, 'stories on', pages, 'pages:') | |
for page in range(0, pages): | |
endpoint = "{0}/{1}/{2}?api_key={3}&per_page=50&page={4}".format(API_URL, 'stories', target_user, STORIFY_API_KEY, page) | |
stories_json = requests.get(endpoint).json() | |
stories.extend(stories_json['content']['stories']) #extend: append all elements from the iterable | |
print ('Retrieved info for', len(stories), 'stories. Downloading elements...') | |
#os.makedirs("{0}".format(target_user), exist_ok=True) | |
progress = 0.0 | |
for story in stories: | |
number_of_elements = sum(story['stats']['elements'].values()) | |
pages = int(math.ceil(number_of_elements / 50))+1 | |
elements = list() | |
for page in range(0, pages): | |
endpoint = "{0}/{1}/{2}/{5}/?api_key={3}&per_page=50&page={4}".format(API_URL, 'stories', target_user, STORIFY_API_KEY, page, story['slug']) | |
elements_json = requests.get(endpoint).json() | |
elements.extend(elements_json['content']['elements']) | |
story['elements'] = elements | |
with open("{0}/{1}.json".format(target_user, story['slug']), 'w') as f: | |
json.dump(story, f) | |
progress += 1.0 | |
print("%.2f%%" % ((progress/number_of_stories)*100.00), 'done. Saved', story['slug'], 'with', len(elements), 'elements...') | |
print('Finished:', target_user) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment