image_spider.py

# -*- coding:utf-8 -*-

import os
import re
import urllib
import json
import socket
import urllib.request
import urllib.parse
import urllib.error
# 设置超时
import time

timeout = 5
socket.setdefaulttimeout(timeout)


class Crawler:
    # 睡眠时长
    __time_sleep = 0.1
    __amount = 0
    __start_amount = 0
    __counter = 0
    __dirname = ""
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.78 Safari/537.36'}

    # 获取图片url内容等
    # t 下载图片时间间隔
    def __init__(self, t=0.1,dirname=""):
        self.time_sleep = t
        self.__dirname = dirname

    # 保存图片
    def __save_image(self, rsp_data,dir, word):
        os.makedirs("./"+dir+"/" + self.__dirname, exist_ok=True)
        # 判断名字是否重复，获取图片长度
        self.__counter = len(os.listdir('./' +dir+"/"+ self.__dirname)) + 1
        for image_info in rsp_data['imgs']:
            try:
                time.sleep(self.time_sleep)
                fix = self.__get_suffix(image_info['objURL'])
                urllib.request.urlretrieve(image_info['objURL'], './'+dir+"/" + self.__dirname + '/' + str(self.__counter) + str(fix))
            except urllib.error.HTTPError as urllib_err:
                print(urllib_err)
                continue
            except Exception as err:
                time.sleep(1)
                print(err)
                print("产生未知错误，放弃保存")
                continue
            else:
                print("图+1,已有" + str(self.__counter) + "张图")
                self.__counter += 1
        return

    # 获取后缀名
    @staticmethod
    def __get_suffix(name):
        m = re.search(r'\.[^\.]*$', name)
        if m.group(0) and len(m.group(0)) <= 5:
            return m.group(0)
        else:
            return '.jpeg'

    # 获取前缀
    @staticmethod
    def __get_prefix(name):
        return name[:name.find('.')]

    # 开始获取
    def __get_images(self,dir, word):
        search = urllib.parse.quote(word)
        # pn int 图片数
        pn = self.__start_amount
        while pn < self.__amount:

            url = 'http://image.baidu.com/search/avatarjson?tn=resultjsonavatarnew&ie=utf-8&word=' + search + '&cg=girl&pn=' + str(
                pn - 120) + '&rn=60&itg=0&z=0&fr=&width=&height=&lm=-1&ic=0&s=0&st=-1&gsm=1e0000001e'
            print(url)
            # 设置header防ban
            try:
                time.sleep(self.time_sleep)
                req = urllib.request.Request(url=url, headers=self.headers)
                page = urllib.request.urlopen(req)
                rsp = page.read().decode('unicode_escape')
            except UnicodeDecodeError as e:
                print(e)
                print('-----UnicodeDecodeErrorurl:', url)
            except urllib.error.URLError as e:
                print(e)
                print("-----urlErrorurl:", url)
            except socket.timeout as e:
                print(e)
                print("-----socket timout:", url)
            else:
                # 解析json
                rsp_data = json.loads(rsp)
                self.__save_image(rsp_data,dir, word)
                # 读取下一页
                print("下载下一页")
                pn += 60
            finally:
                page.close()
        print("下载任务结束")
        return

    def start(self,dir, word, spider_page_num=1, start_page=1):
        """
        爬虫入口
        :param word: 抓取的关键词
        :param spider_page_num: 需要抓取数据页数 总抓取图片数量为 页数x60
        :param start_page:起始页数
        :return:
        """
        self.__start_amount = (start_page - 1) * 60
        self.__amount = spider_page_num * 60 + self.__start_amount
        self.__get_images(dir,word)


if __name__ == '__main__':


    name_arr = ["亚洲女"]
    dir_name = ['nv']

    count = 0
    for name in name_arr:
        print(dir_name[count],name_arr[count])
        crawler = Crawler(0.05, dir_name[count])
        crawler.start("download_img",name_arr[count], 10, 3)
        count += 1