fayingting

# coding=utf-8
from selenium import webdriver
from bs4 import BeautifulSoup
import time
driver=webdriver.Chrome()
driver.set_page_load_timeout(10)
try:
    driver.get("http://music.163.com/#/song?id=409060868")
except selenium.common.exceptions.TimeoutException:
    print("time out of 10 s")

fayingting

# coding=utf-8
from numpy import *
import operator
# 分类器inx为预测数据集，dataset为训练数据集，labels为训练数据集中的标签
def classify(inx,dataset,labels,k):
    # 求预测数据集与训练数据集的距离
    datasize=dataset.shape[0]
    d=tile(inx,(datasize,1))-dataset
    dd=d**2
    distance=(dd.sum(axis=1))**0.5

fayingting

# coding=utf-8
import urllib2
from bs4 import BeautifulSoup
class BDTB:
    def __init__(self,baseurl,seeLZ,floorTag):
        self.baseurl=baseurl
        self.seeLZ='?see_lz='+str(seeLZ)
        self.file=None
        self.floor=1
        self.floorTag=floorTag

fayingting

# coding=utf-8
# 测试数据集
def sampletrain(cl):
    cl.train('Nobody owns the water.', 'good')
    cl.train('the quick rabbit jumps fences', 'good')
    cl.train('buy pharmaceuticals now', 'bad')
    cl.train('make quick money at the online casino', 'bad')
    cl.train('the quick brown fox jumps', 'good')
# 正则表达式从文本中提取特征
import re