Fetch devopreaction.tumbrl.com

fetch

#!/usr/bin/env python

api_key = "" #API KEY
blog = "devopsreactions.tumblr.com"
url_info = "https://api.tumblr.com/v2/blog/{blog}/info?api_key={api_key}"
url_posts = "https://api.tumblr.com/v2/blog/{blog}/posts/text?api_key={api_key}&offset={offset}"


def get_info():
	return url_info.format(api_key=api_key, blog=blog)
def get_posts(offset=0):
	return url_posts.format(api_key=api_key, blog=blog, offset=offset)


import json
import urllib2
import re
import os.path
import urllib

offset = 0
while(True):
	data = json.load(urllib2.urlopen(get_posts(offset)))
	if data["meta"]["msg"].encode("utf-8") != "OK":
		print("Error: ")
		print(data)
		break

	response = data["response"]
	print("[{p}%]".format(p = 100 * offset / response["blog"]["posts"]))
	for post in response["posts"]:
		body = post["body"].encode('utf-8')
		
		p = re.compile(ur'src="(http.+\.gif)"')
		imgs = re.findall(p, body)
		if len(imgs) == 0 or not post["title"]:
			continue

		title = post["title"].encode('utf-8')
		title = title.replace("/", " - ")
		name = blog + "/" + title + ".gif"

		if os.path.isfile(name):
			print("[OK]: {name}".format(name=name))
		else:
			
			urllib.urlretrieve (imgs[0], name)
			print("[OK: {size}b] {name}".format(name=name, size=os.path.getsize(name)))

		if os.path.getsize(name) < 3500:
			print("[WARNING] Suspected size, will be removed")
			os.remove(name)

	if response["blog"]["posts"] > offset:
		offset += len(response["posts"])
	else: 
		break