# -*- coding:utf-8 -*-
import os
import time
import requests
import urllib
import uuid
from pyquery import PyQuery

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                  "Chrome/75.0.3770.142 Safari/537.36"
}


def href_url_download():
    # 1.填写要爬取关键词的list.txt
    keyword_list = open("list.txt", 'r', encoding='utf-8')
    lines = keyword_list.readlines()
    keyword_list.close()
    for keyword in lines:
        keyword = keyword.strip()
        print(keyword)
        # 2.修改爬取的页数(1,101),默认爬取100页
        for pages in range(1, 3):
            page = str(pages)
            url = "https://pixabay.com/zh/images/search/" + keyword + "/?pagi=" + page  # 获取keyword网页
            # print(url)
            try:
                txt = requests.get(url, headers=headers).text  # 获取URL及headers
                doc = PyQuery(txt)
                # print(doc)
                urls = doc(".item a img ").items()
                for url in urls:
                    image_url = url.attr("data-lazy")
                    if image_url is None:
                        continue
                    else:
                        print(image_url)
                        image_download(keyword, image_url)  # 下载"图片"
            except requests.exceptions.ConnectionError as e:
                print("requests.exceptions.ConnectionError")


def image_download(keyword, image_url):
    # 3.图片存储路径
    folder_path = "./image/" + keyword + "/"
    if not os.path.exists(folder_path):
        os.makedirs(folder_path)
        # print(folder_path)
    image = keyword + "_" + str(uuid.uuid1()) + ".jpg"  # 图片命名
    print(image)
    # urllib.request.urlretrieve(href3, folder_path + "/" + image)
    try:
        content = requests.get(image_url, headers=headers)
        with open(folder_path + image, "wb") as f:
            f.write(content.content)
    except urllib.error.HTTPError:
        print("Internal Server Error")
    except requests.exceptions.ConnectionError as e:
        print("requests.exceptions.ConnectionError")


if __name__ == '__main__':
    href_url_download()