class ImageFinder:
def __init__(self):
self.language = Language()
def find(self, lyrics, limit=None):
nouns = self.language.get_top_nouns(lyrics)
limited_nouns = nouns[:len(nouns) if limit is None
or limit >= len(nouns) else limit]
if debug:
print('Nouns: ' + ','.join(nouns))
if limit is not None:
print('Limiting to ({}): {}'.format(limit,
','.join(limited_nouns)))
images = []
for noun in limited_nouns:
try:
images.append((self.get_images(noun, 1)[0], noun))
except:
pass
return images
@staticmethod
def get_images(q, cnt):
query = q
if debug:
print('Query: ' + q)
query = query.split()
query = '+'.join(query)
url = "https://www.google.com/search?q=" + query + "&source=lnms&tbm=isch&tbs=itp:clipart,ic:trans"
if debug:
print('Query url: ' + url)
header = {
'User-Agent':
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36"
}
if debug:
print('Making request...')
soup = BeautifulSoup(
urllib2.urlopen(urllib2.Request(url, headers=header)),
'html.parser')
if debug:
print('Parsing response...')
actual_images = []
for a in soup.find_all("div", {"class": "rg_meta"}):
link, Type = json.loads(a.text)["ou"], json.loads(a.text)["ity"]
actual_images.append((link, Type))
if debug:
print('Processing images...')
images = []
for i, (img, Type) in enumerate(actual_images[:cnt]):
try:
req = requests.get(img)
raw_img = Image.open(io.BytesIO(req.content))
raw_img.thumbnail((152, 152), Image.ANTIALIAS)
wid = raw_img.size[0] / 2
hgt = raw_img.size[1] / 2
#raw_img = raw_img.crop((wid - 64, hgt - 64, wid + 64, hgt + 64))
images.append(np.asarray(raw_img))
except Exception as e:
print("could not load : ", img)
print('Finished query.')
return images
