python爬虫学习1

首先感谢刘鸿亮的文章-python爬虫之图片爬虫，学习过程中采用了其中的思路和代码，特此声明！
文章链接：python爬虫之图片爬虫
下面为我的代码，初次学习，望原谅。
爬取图片的目标网站：天堂图片网

import os
import re
import requests
from bs4 import BeautifulSoup

#获取页面数据
def get_data(url):
    response = requests.get(url)
    if response.status_code == 200:
        data = response
        return data
    return None

#获取不同类别图片的链接
def get_category(url):
    category_it = []
    data = get_data(url)
    soup = BeautifulSoup(data.text,'lxml')
    all = soup.find_all('div',class_ = 'kw')
    for div in all:
        href = url + div.a.get('href')
        category_it.append(href)
    return category_it

#获取不同组图片链接
def get_group(group):
    tu_it = []
    data = get_data(group)
    reg = r'/tupian/\w*?/'
    pattern = re.compile(reg)
    a = re.findall(pattern, data.text)[:18]
    for tu in a:
        tu_web = url + tu
        tu_it.append(tu_web)
    return tu_it

#获取图片链接
def get_web(web):
    web_it = []
    for w in range(2,6):
        tu_web = web + "index_" + str(w) + ".html"
        data = get_data(tu_web)
        soup = BeautifulSoup(data.text,'lxml')
        all = soup.find_all('div',class_ = 'il_img')
        for div in all:
            href = url + div.a.get('href')
            web_it.append(href)
    return web_it

#下载图片
def download(down_url,dir):
#     group_web = get_group(url)
#     for g in group_web:
        data = get_data(down_url)
        soup = BeautifulSoup(data.text,'lxml')
        all = soup.find_all('div',class_ = 'il_img')
        get_dir("img_folder_" + dir)
        num = 1
        for div in all:
            href = div.img.get('src')
            try:
                img = get_data(href)
                with open("pic_%s.jpg" % num, 'wb') as p:
                    p.write(img.content)
                    num += 1
            except Exception:
                print("Picture not exist!")

# 创建并进入文件夹
def get_dir(dir):        
    a = os.path.abspath('.')
    b = os.path.join(a, dir)
    if not os.path.exists(b):
        os.mkdir(dir)
        os.chdir(b)
    else:
        os.chdir(b)

# 退出当前文件夹
def return_dir():     
    d = os.path.split(os.path.abspath("."))[0]
    os.chdir(d)

def go(url):
    category_lt = get_category(url)
    a = 1
    for i in category_lt:
        get_dir("category_" + str(a))
        group_lt = get_group(i)
        n = 1
        for web in group_lt:
            num = 1
            get_dir("group_" + str(n))
            print("The group is: " + str(n))
            for ii in get_web(web):
                download(ii, str(num))
                num += 1
            n += 1
            return_dir()
        a += 1
        return_dir()

if __name__ == '__main__':
    url = "http://www.ivsky.com/"
    get_dir("test1")
    go(url)