# -*- coding=utf-8 -*-
import xlwings as xw
import urllib
import sys

type = sys.getfilesystemencoding() 

def get_html(url):
  page = urllib.urlopen(url)
  html = page.read()
  return unzip(html)

## Debug的时候发现无论怎样做Decode，最后的结果都是乱码
## 后来发现是因为对应的网页做了压缩处理，所以需要对获取的网页内容手动解压缩
def unzip(data):
  import gzip
  import StringIO
  data = StringIO.StringIO(data)
  gz = gzip.GzipFile(fileobj=data)
  data = gz.read()
  gz.close()
  return data

wb = xw.Book(r"C:\Users\hasee\Desktop\Test.xlsx")
main_data = wb.sheets["Sheet2"]
## 通过获取Last Cell来确定当前Sheet的有效行数与列数
rownum = main_data.range('A1').current_region.last_cell.row
colnum = main_data.range('A1').current_region.last_cell.column

## 定位column对应的列
col_dict = {"2":"B","3":"C","4":"D","5":"E","6":"F"}

for row in range(1, rownum + 1):
  for col in range(2, colnum + 1):
    query = main_data.range(row, 1).value
    cell = main_data.range(row, col)
    link = cell.hyperlink
    html = get_html(link)
    if "error-container" in html:
      print "%s,%s,%s,%s" % (query, col_dict.get(str(col))+str(row), cell.value, cell.hyperlink)
      ## 对无效的链接所属的Cell染色，直接写入文件
      cell.color = (253,218,4)