{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os,urllib3\nimport pandas as pd\nfrom multiprocessing import Pool\nfrom multiprocessing.dummy import Pool as ThreadPool\nfrom PIL import Image\nfrom io import BytesIO\nfrom tqdm import tqdm\nimport requests","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"colors = ['red','green','blue','yellow']\nDIR = \"../HPAv18/\"\nv18_url = 'http://v18.proteinatlas.org/images/'\nsave_dir = '../' #Change the save path","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"43cd57186bebe8dc182f12af727dfdcdae4c63ab"},"cell_type":"code","source":"os.listdir('../input')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"50e191bf0b064cf527eb18ea72ce586438b90214"},"cell_type":"code","source":"imgList = pd.read_csv('../input/hpav18/HPAv18RBGY_wodpl.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"19b426d165442b3124937bedb036e0d60d59ebfe"},"cell_type":"code","source":"url_key = []\nfor i in imgList['Id'][74596:]: #Default download all data, for kernel example, I only download 10 image \n    img = i.split('_')\n    for color in colors:\n        img_path = img[0] + '/' + \"_\".join(img[1:]) + \"_\" + color + \".jpg\"\n        img_name = i + \"_\" + color + \".jpg\"\n        img_url = v18_url + img_path\n        url_key.append((img_name, img_url))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8b8a706ab5d3c73f487aaae9fc33c4db66df844e"},"cell_type":"code","source":"def DownloadImage(key_url):\n\n    (key, url) = key_url\n    filename = key\n    r = requests.get(url, allow_redirects=True)\n    img_save = Image.open(BytesIO(r.content)).resize((512, 512),Image.ANTIALIAS)\n    if len(img_save.getbands())> 1:\n        red, green, blue = img_save.split()\n        if 'red' in filename:\n            red.save(save_dir+filename[:-4]+'.png','png')\n        if 'blue' in filename:  \n            blue.save(save_dir+filename[:-4]+'.png','png')\n        if 'green' in filename:\n            green.save(save_dir+filename[:-4]+'.png','png')\n        if 'yellow' in filename:\n            Image.blend(red,green,0.5).save(save_dir+filename[:-4]+'.png','png')\n    else:\n        img_save.save(save_dir+filename[:-4]+'.png','png')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ce37135638da492922fa5b6fed1aa29f12789124"},"cell_type":"code","source":"def Run():\n\n  pool = ThreadPool(processes=100)\n\n  with tqdm(total=len(url_key)) as bar:\n    for _ in pool.imap_unordered(DownloadImage, url_key):\n      bar.update(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d8be1c3fac1d123210069a896af5875ded6dc98f"},"cell_type":"code","source":"if __name__ == '__main__':\n  Run()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8ce01b57dcba84ea2171fbcf40bb957e1d4e1a06"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}