下厨房图片爬虫

# -*- 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():
    # 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(1,14),默认爬取13页
        for pages in range(1, 14):
            page = str(pages)
            # https://www.xiachufang.com/search/?keyword=华夫饼&cat=1001&page=2
            url = "https://www.xiachufang.com/search/?keyword=" + keyword + "&cat=1001&page= " + page
            # print(url)
            try:
                txt = requests.get(url, headers=headers).text
                doc = PyQuery(txt)
                # print(doc)
                pages_url = doc(".pure-u .name a").items()
                for page_url in pages_url:
                    img_url = page_url.attr("href")
                    img_urls = "https://www.xiachufang.com/" + img_url
                    # print(img_urls)
                    txt2 = requests.get(img_urls, headers=headers).text
                    doc2 = PyQuery(txt2)
                    # print(doc2)
                    images = doc2(".block-negative-margin img").items()
                    for image in images:
                        image_url = image.attr("src")
                        print(image_url)
                        image_download(keyword, image_url)
            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)
    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()