给面小站网站图片爬虫

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

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():  # 一.获取"图片的URL"
    # 花(1,28)
    for pages in range(1, 28):
        page = str(pages)
        url = "https://www.geimian.com/wx/tag/花卉/page/" + page  # 1.第一级网页分析
        # print(url)
        txt = requests.get(url, headers=headers).text  # 2.获取第一级网页URL及headers
        doc = PyQuery(txt)
        # print(doc)
        pages_url = doc(".index_wz_lb>a").items()  # 3.分析第一级网页特点
        for page_url in pages_url:
            img_url = "https:" + page_url.attr("href")  # 4.获取第二级网页
            print(img_url)
            txt2 = requests.get(img_url, headers=headers).text  # 5.获取第二级网页URL及headers
            doc2 = PyQuery(txt2)
            # print(doc2)
            class_name = doc2("#db_biaoti h2").text()  # 7.获取到标签所有页面
            print(class_name)
            images_url = doc2("#imgbdjz #inr_zx p img").items()  # 6.分析第二级网页特点
            images_url1 = doc2("#imgbdjz #xcnr_zx p img").items()  # 6.分析第二级网页特点
            # 二.下载"图片"
            image_download(images_url, images_url1, class_name)


def image_download(images_url, images_url1, class_name):  # 二.下载"图片"
    folder_path = "image/" + class_name
    if not os.path.exists(folder_path):
        os.makedirs(folder_path)
        # print(folder_path)
        for image in images_url:
            image_url = image.attr("title")
            print(image_url)
            image_name = class_name + "_" + str(uuid.uuid1()) + ".jpg"
            content = requests.get(image_url, headers=headers)
            with open(folder_path + "/" + image_name, "wb") as f:
                f.write(content.content)
        for image1 in images_url1:
            image_url1 = image1.attr("title")
            print(image_url1)
            image_name = class_name + "_" + str(uuid.uuid1()) + ".jpg"
            content = requests.get(image_url1, headers=headers)
            with open(folder_path + "/" + image_name, "wb") as f:
                f.write(content.content)


if __name__ == '__main__':
    # 1.一.获取"图片的URL"
    href_url_download()