def LEASE_NTC_INIT():
current_page = get_web_page(
LEASE_URL, urlJumpIp) # return a dict of dict of list of dict
total_rows = get_total_rows(current_page)
page_count = 0
row_data = []
while page_count <= total_rows:
data = get_info(current_page)
row_data += data
page_count += pageRow
current_page = get_web_page(
LEASE_URL + "&firstRow=" + str(page_count) + "&totalRows=" +
str(total_rows), urlJumpIp)
progress(page_count, total_rows, __file__)
save(row_data)
print(str(__file__) + " complete")
def INFO_BOX_TPE_INIT():
row_data = read_excel("sells/data/TPE/info/total_rows_TPE.xlsx") # get the excel info
info_boxes = []
for data in row_data:
page = get_web_page(DETAIL_URL + data["url"], urlJumpIp)
info_boxes += get_info_box(page, data["post_id"])
showProgess(__file__)
save(info_boxes, "sells/data/TPE/info/info_box_TPE")
print(str(__file__) + " complete")
def HOUSE_BOX_TPE_INIT():
row_data = read_excel("lease/data/TPE/info/total_rows_TPE.xlsx") # get the excel info
house_boxes = []
for data in row_data:
page = get_web_page(DETAIL_URL + data["url"], urlJumpIp)
house_boxes += get_house_box(page, data["post_id"])
showProgess(__file__)
save(house_boxes, "lease/data/TPE/info/house_box_TPE")
print(str(__file__) + " complete")
def IMG_TPE_INIT():
row_data = read_excel(
"sells/data/TPE/info/total_rows_TPE.xlsx") # get the excel info
dir = "D:/Python/database/sells/images/TPE/"
if os.path.exists(dir): # 先刪除原本的images資料夾
shutil.rmtree(dir, ignore_errors=True)
for data in row_data:
page = get_web_page(DETAIL_URL + data["url"], urlJumpIp)
img_urls = get_images(page)
save(img_urls, data["post_id"], dir)
showProgess(__file__)
print(str(__file__) + " complete")