def _image_doc(self, folder, rel_path):
full_path = os.path.join(folder, rel_path)
args = ['--metadata']
if 'time_zone' in self._source:
args.extend(['--timezone', self._source['time_zone']])
args.extend(['--thumbnail', '64', '--thumbnail', '512'])
doc, logs = image.get(full_path, *args)
for log in logs:
log['path'] = "%s/%s" % (self._source['_id'], rel_path)
self._log.append(log)
if not doc:
return
if 'original_info' in doc:
del doc['original_info']
doc['_id'] = "img-%s" % uuid.uuid4().hex
doc[IMAGE_TYPE] = True
idents = doc.setdefault('identifiers', {})
idents['path'] = {'source':couch.make_ref(self._source), 'name':rel_path}
with open(full_path, 'rb') as f:
md5 = hashlib.md5()
sha1 = hashlib.sha1()
while True:
buff = f.read(524288)
if not buff:
break
md5.update(buff)
sha1.update(buff)
idents['md5'] = md5.hexdigest()
idents['sha1'] = sha1.hexdigest()
return doc
def __init__(self):
import image
self.colors = image.random_color_scheme("personal")
print self.colors
self.sprites = [image.get("cha_f_mechanic.png", self.colors, (64*(i%4), 64*(i//4), 64, 64)) for i in range(8)]
self.orientation = 0
self.map = None
self.coords = (0,0)
def save_histogram_to_frontend(self, histogramArr):
graylevel = self.mainImageObject.getGrayLevel()
arrTemp = np.zeros((3, graylevel), dtype='uint8')
for i in range(3):
for j in range(graylevel):
arrTemp[i][j] = image.get(histogramArr, i, j)
return arrTemp
def _get_jpeg(self, image_path, size, metadata=False):
name = 'export' if metadata else 'thumbnail'
doc, _ = image.get(image_path, '--%s' % name, size)
if doc:
img = doc.get('_attachments', {}).get('%s/%s.jpg' % (name, size))
if img:
headers = {'Content-Type':img['content_type']}
return {'code':200, 'headers':headers, 'base64':img['data']}
return {'code':500, 'json':{'error':True, 'reason':"Failed to get image"}}
def save_array_to_frontend(self, imgObject):
arrTemp = np.zeros((imgObject.getHeight(), imgObject.getWidth(), 3),
dtype='uint8')
for i in range(imgObject.getHeight()):
for j in range(imgObject.getWidth()):
for k in range(3):
arrTemp[i][j][k] = image.get(imgObject.getPixels(), i, j,
k)
return arrTemp
def __init__(self, map_to_draw):
self.view_x = 0
self.view_y = 0
self.map_to_draw = map_to_draw
self.mouse_cursor = image.get("target64.png", None, (0,0,64,64))
def sprite(self):
if self._sprite is None:
self._sprite = image.get(*self.sdl_image_spec)
return self._sprite
def main(pages):
global _IMAGE_CNT, _VIDEO_CNT
for i in range(pages):
url = _GRAP_URL + '&page=' + str(i)
html_doc = urllib.urlopen(url).read()
if html_doc:
soup = BeautifulSoup(html_doc)
try:
# ============================================================
# 采集视频
# ============================================================
target_divs = soup.find_all('article', {'class': 'post-video'})
if target_divs and len(target_divs):
for td in target_divs:
# 资源标题
title = td.find('h2')['title']
video_src = td.find('embed')['src'].strip()
# FIXME url
video_id = _get_video_id('http://player.56.com/renrenshare_(.*).swf/1030_.*.swf', video_src)
if not video_id:
continue
# 获取视频信息
video_info = _get_video_info(video_id)
if video_info.get('info', None):
video_img = video_info['info']['bimg']
# 不抓取重复资源
if db.exists(video_src):
continue
resource_info = _deal_resource(video_img)
resource_info['url'] = video_src
resource = db.SpideResource(title, 'video', json.dumps(resource_info), video_src)
db.save(resource)
print '成功爬取视频资源!'
_VIDEO_CNT = _VIDEO_CNT + 1
else:
print 'Fail to get video_info by: %s %s' % (video_src, video_id)
except Exception, err:
print '[VideoError] ' + str(err)
try:
# ============================================================
# 采集图片
# ============================================================
target_divs = soup.find_all('article', {'class': ['post-photo', 'post-article']})
if target_divs and len(target_divs):
for td in target_divs:
post_content = td.find('div', {'class': 'post-content'})
# 资源标题
title = post_content.find('h2')['title']
images = post_content.find_all('img')
# 抓取只有一副图片的资源
if images and len(images) == 1:
image = images[0]
if image.get('data-src', None):
image_src = image['data-src'].strip()
else:
image_src = image['src'].strip()
# 不抓取重复资源
if db.exists(image_src):
continue
resource_info = _deal_resource(image_src)
resource = db.SpideResource(title, 'image', json.dumps(resource_info), image_src)
db.save(resource)
print '成功爬取图片资源!'
_IMAGE_CNT = _IMAGE_CNT + 1
except Exception, err:
print '[ImageError] ' + str(err)
def sprite(self):
if self.orien==Door.OR_HORI: x=64
else: x=0
y = 0
if not self.closed: y = 96
return image.get("door_a.png", None, (x,y,64,96))
if cmd == "help":
print("SmartTrash控制台帮助")
print("about或version-----显示版本信息")
print("help-----显示此帮助")
print("stop或exit-----退出程序")
print("")
elif cmd == "stop" or cmd == "exit":
stop()
elif cmd == "about" or cmd == "version":
about()
elif cmd == "take":
image.take()
elif cmd == "imgc":
image.image_classify(image.image)
elif cmd == "get":
image.get()
elif cmd == 'type':
image.getType(image.result['result'][0]['keyword'] + '/' +
image.result['result'][0]['root'])
elif cmd == 'run':
run()
elif cmd == 'setdist':
distance.distmin = float(input('input the distmin:'))
elif cmd == 'setdisttime':
distance.whiletime = float(input('input the whiletime:'))
elif cmd == '':
pass
else:
print("未知命令 输入help查看帮助")
cmd = ""
# --------------------------------------