def img_download(root_path, img_url):
#1. 获取下载图集信息
img_info = get_img_info(img_url)
img_name = img_info["img_name"]
img_count = int(img_info["img_count"])
#2.创建图片保存路径
save_folder = root_path + "/" + img_name
file_utils.mkdir_path(save_folder)
#3.开始图集下载
img_type_id = img_url[img_url.rfind("a") + 2:img_url.rfind("/")]
logging.info("当前[%s]图集下载地址:%s" % (img_name, img_url))
logging.info("当前[%s]图集下载总数img_count=%s,img_type_id=%s" %
(img_name, img_count, img_type_id))
for index in range(img_count):
img_download_url = cf.get("base_config", "img_download_url")
img_download_url = img_download_url.format(img_type_id, index)
# logging.info("当前图片下载地址:%s" % (img_download_url))
file_download_utils.img_download(save_folder, img_download_url)
logging.info("当前[%s]图集下载完成" % (img_name))
log_name = cf.get("default_config", "log_name")
get_type = cf.get("base_config", "get_type") # 该参数暂时未生效,未来可能需要实现方式
data_type = cf.get("base_config", "data_type")
root_path = cf.get("base_config", "root_path")
curr_date = file_utils.get_curr_date()
curr_root_path = config.get_curr_root_path(root_path, data_type, curr_date)
tips = "===============================\n" \
"程序运行前先对base_config.ini进行配置：\n" \
"https://github.com/xiaodeme \n" \
"运行日志请查看 logs/data_collection.log \n" \
"==============================="
print tips
# 日志初始化配置
log_foloder_name = curr_root_path + "/logs/"
file_utils.mkdir_path(log_foloder_name)
log_utils.log_config(log_foloder_name + LOG_NAME)
#1. 初始化程序运行配置基础信息
config.init_config(root_path, data_type, get_type)
config_dict = config.get_config(root_path, data_type, curr_date)
#2. 开始采集
run_result = data_list_collection.data_collection(config_dict)
if run_result < 1:
logging.error("[1]执行不成功，终止程序运行:%s" % (run_result))
#清空当天文件夹
data_list_folder_name = config_dict["data_list_folder_name"]
if file_utils.clear_folder(data_list_folder_name):
logging.info("清空文件夹文件:%s" % (data_list_folder_name))
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
from utils import etc_utils
from utils import access_data_utils
from utils import file_utils
#获取配置信息
dataTypeConfig = etc_utils.DataTypeConfig(26, "../etc/example1_get_type.cfg")
save_root_path = dataTypeConfig.get_save_root_path()
total_count = int(dataTypeConfig.get_total_count())
#data_list数据保存路径
DATA_LIST_PATH = save_root_path + "/data_list/"
file_utils.mkdir_path(DATA_LIST_PATH)
# 器械详情保存路径
DATA_INFO_PATH = save_root_path + "/data_info/"
file_utils.mkdir_path(DATA_INFO_PATH)
#日志保存路径
LOG_PATH = save_root_path + "/logs/"
file_utils.mkdir_path(LOG_PATH)
#获取采集数据Id集合
file_list = file_utils.get_file_list(DATA_LIST_PATH)
id_list = file_utils.get_all_data_id(file_list)
print("采集数据总量:%s" % (id_list.qsize()))
'''
获取data_info数据
(img_name, img_count, img_type_id))
for index in range(img_count):
img_download_url = cf.get("base_config", "img_download_url")
img_download_url = img_download_url.format(img_type_id, index)
# logging.info("当前图片下载地址:%s" % (img_download_url))
file_download_utils.img_download(save_folder, img_download_url)
logging.info("当前[%s]图集下载完成" % (img_name))
if __name__ == '__main__':
root_path = cf.get("base_config", "root_path")
index_url = cf.get("base_config", "index_url")
file_utils.mkdir_path(root_path)
log_name = root_path + "/" + "log.log"
log_utils.log_config(log_name)
print("图集正确地址查看:%s" % (index_url))
print("图集正确输入地址:%s" % ("https://www.meituri.com/a/22523/"))
# href = 'https://www.meituri.com/a/22523/'
href = raw_input('请输入图集下载类型：')
print("您输入的图集地址是:%s" % (href))
print("当前图集保存文件夹:%s " % (root_path))
print("当前图集下载日志查看:%s " % (log_name))
img_download(root_path, href)