def cal_similarity(image_name, image_files, directory):
# rdb.set_trace()
original = io.imread(os.path.join(directory, image_name))
original = rgb2gray(original)
similarity = {}
for image in image_files:
if image_name != image:
compare = rgb2gray(io.imread(os.path.join(directory, image)))
sim = ssim(original, compare)
if len(similarity) >= 2:
min_ssim = min(similarity, key=similarity.get)
if sim > similarity[min_ssim]:
del similarity[min_ssim]
else:
continue
similarity[image] = sim
# update the cache
if image in redis_cache.keys():
image_similarity = pickle.loads(redis_cache.get(image))
if len(image_similarity) < 2:
image_similarity[image_name] = sim
redis_cache.set(image, pickle.dumps(image_similarity, pickle.HIGHEST_PROTOCOL))
min_ssim = min(image_similarity, key=image_similarity.get)
if sim > image_similarity[min_ssim]:
del image_similarity[min_ssim]
image_similarity[image_name] = sim
redis_cache.set(image, pickle.dumps(image_similarity, pickle.HIGHEST_PROTOCOL))
return similarity
def get_content(url):
if redis_cache.get(url):
resp = redis_cache.get(url)
resp = json.loads(resp.decode('utf-8'))
print resp, "item loaded from cache"
else:
resp = cli.oembed(url, raw=True, words = 30)
if resp.get('raw'):
r = redis_cache.set(url, resp.get('raw'))
print 'item cached:', r
else:
resp = lassie.fetch(url)
j = json.dumps(resp)
r = redis_cache.set(url, j)
print resp
if resp:
if resp.get("provider_name") == "Twitter":
return render_twitter(url)
elif resp.get("provider_name") == "YouTube":
return render_youtube(resp.get("html"))
elif resp.get("type") == "rich":
print "rich"
ratio = (float(resp.get("height",1))/resp.get("width",1))*100
print ratio
if ratio <= 0:
ratio = 100
return render_template("video.html", content = resp.get("html"), ratio = str(ratio))
elif resp.get("type") == "video":
print "video"
ratio = (float(resp.get("height", 1))/resp.get("width",1))*100
print ratio
if ratio <= 0:
ratio = 100
return render_template("video.html", content = resp.get("html"), ratio = ratio)
elif resp.get("type") == "link":
return render_template("article.html", title = resp.get("title"), image=resp.get("thumbnail_url"), description = resp.get("description"), _url=resp.get("url"), provider = resp.get("provider_name"))
elif resp.get("type") == "photo":
print "photo"
return render_template("photo.html", _url = str(resp.get("url")), source = url)
else:
return render_nostyle(url)
else:
return render_nostyle(url)
def render_nostyle(url):
resp = redis_cache.get(url)
print resp, type(resp)
if not resp:
resp = lassie.fetch(url)
resp = json.dumps(resp)
r = redis_cache.set(url, resp)
else:
resp = json.loads(resp)
thumbnail = resp.get('images')
if thumbnail:
thumbnail = thumbnail[0].get('src')
title = resp.get('title')
description = resp.get('description')
parse_obj = urlparse(url)
provider = parse_obj.netloc
return render_template('article.html', _url = url, image = thumbnail, title = title, description = description, provider=provider)
def cache_urls(urls):
#check which urls are not in the cache
not_cached_urls = []
for u in urls:
r = redis_cache.get(u)
if not r:
not_cached_urls.append(u)
#takes a list and splits it into a list of lists of size n
def chunks(u, n=20):
for i in xrange(0, len(urls), n):
yield urls[i:i + n]
#send each batch to the embedly api and cache the results
for batch in list(chunks(not_cached_urls)):
resp = cli.oembed(batch, raw=True, words=30)
for i in resp:
c = redis_cache.set(i.get(original_url), i.get('raw'))
print 'Item cached', c
return True
def details(image_name):
similarity = {}
if image_name in redis_cache.keys():
similarity = pickle.loads(redis_cache.get(image_name))
similarity = collections.OrderedDict(sorted(similarity.items(), key=lambda x: x[1], reverse=True))
return render_template("details.html", image=image_name, similar=similarity)