zhiyu_content_spider/content_spider/temp_test.py

# -*- coding: utf-8 -*-
import hashlib
import json
import re
from urllib.parse import urlencode
from urllib.parse import urlsplit
from urllib.parse import unquote
from urllib.parse import parse_qs

import urllib
from xml.dom.minidom import parseString

import time
import xlrd






def get_category(c_id):
    if c_id == '1001001' or c_id == '1001002':
        return {"id":67,"name":"校园励志"}
    if c_id == '1001003':
        return {"id":30,"name":"校园黑道"}
    if c_id == '1001004' or c_id == '1001005':
        return {"id":94,"name":"青春爱情"}
    if c_id == '1002001'  or c_id == '1002004':
        return {"id":54,"name":"都市爱情"}
    if c_id == '1002002':
        return {"id":68,"name":"现代修真"}
    if c_id == '1002003':
        return {"id":55,"name":"官场沉浮"}
    if c_id == '1003001' or c_id == '1003002' or c_id == '1003003' or c_id == '1003004':
        return {"id":81,"name":"灵异恐怖"}
    if c_id == '1004001'or c_id == '1004002' or c_id == '1004003' or c_id == '1004004':
        return {"id":14,"name":"历史穿越"}
    if c_id == '1005001'or c_id == '1005002' or c_id == '1005003' or c_id == '1005004' or c_id == '1006001'or c_id == '1006002' or c_id == '1006003' or c_id == '1006004':
        return {"id":23,"name":"玄幻奇幻"}
    if c_id == '1007001' or c_id == '1007002' or c_id == '1007003' or c_id == '1007004':
        return {"id":19,"name":"游戏竞技"}
    
    if c_id == '1008001' or c_id == '1008002'  or c_id == '1008003'  or c_id == '1008004'  or c_id == '1008005':
        return {"id":98,"name":"婚恋情感"}
    if c_id == '1009001' or c_id == '1009002':
        return {"id":120,"name":"宫斗宅斗"}
    if c_id == '1009003' or c_id == '1009004' or c_id == '1009005':
        return {"id":123,"name":"女尊王朝"}
    if c_id == '1010001' or c_id == '1010002' or c_id == '1010003' or c_id == '1010004' or c_id == '1010005':
        return {"id":98,"name":"婚恋情感"}
    if c_id == '1011001' or c_id == '1011002' or c_id == '1011003' or c_id == '1011004' or c_id == '1011005' or c_id  == '1011006':
        return {"id":96,"name":"东方玄幻"}
    

wb = xlrd.open_workbook("fff.xls")
sh1 = wb.sheet_by_index(0)

print( u"sheet %s 共 %d 行 %d 列" % (sh1.name, sh1.nrows, sh1.ncols))
last_cate_id = 0
last_channel_id = 0
result = []
for item in range(1,sh1.nrows):
	rows = sh1.row_values(item)
	if rows[0] == '':
		channel_id = last_channel_id
	else:
		channel_id = 1 if rows[0] == '男频' else 2
		last_channel_id = channel_id
	if rows[1] == '' or  rows[1] is None:
		cate_id = last_cate_id
	else:
		cate_id = int(rows[1])

	last_cate_id = cate_id

	cate_name = rows[2]
	sub_cate_id = int(rows[3])
	sub_cate_name = rows[4]
	category_info = get_category(str(sub_cate_id))
	result.append({
        "channel_id":channel_id,'cate_id':str(cate_id),'cate_name':cate_name,'sub_cate_id':str(sub_cate_id),'category_id':category_info['id'],'category_name':category_info['name']
	})
    
	#print(channel_id)
print(result)