爬取爱套图网图片：https://github.com/EExplode/scrapy_aitaotu

一.保存至MongoDB

import pymongo


class MongoPipeline(object):
    # 初始化参数
    def __init__(self, mongo_uri, mongo_db):
        self.mongo_uri = mongo_uri
        self.mongo_db = mongo_db

    # 以依赖注入的方式获取settings.py中的配置信息
    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            mongo_uri=crawler.settings.get('MONGO_URI'),
            mongo_db=crawler.settings.get('MONGO_DB')
        )

    # Spider开启时，初始化数据库连接
    def open_spider(self, spider):
        self.client = pymongo.MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]

    # 将item插入MongoDB，集合定义在item中
    def process_item(self, item, spider):
        self.db[item.collection].insert(dict(item))
        return item

    # Spider结束后，关闭数据库连接
    def close_spider(self, spider):
        self.client.close()

二.保存至MySQL

import pymysql


class MysqlPipeline(object):
    def __init__(self, host, database, user, password, port):
        self.host = host
        self.database = database
        self.user = user
        self.password = password
        self.port = port

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            host=crawler.settings.get('MYSQL_HOST'),
            database=crawler.settings.get('MYSQL_DATABASE'),
            user=crawler.settings.get('MYSQL_USER'),
            password=crawler.settings.get('MYSQL_PASSWORD'),
            port=crawler.settings.get('MYSQL_PORT'),
        )

    def open_spider(self, spider):
        self.db = pymysql.connect(self.host, self.user, self.password, self.database, charset='utf8', port=self.port)
        self.cursor = self.db.cursor()

    def close_spider(self, spider):
        self.db.close()

    def process_item(self, item, spider):
        data = dict(item)
        keys = ', '.join(data.keys())
        values = ', '.join(['%s'] * len(data))
        sql = 'insert into %s (%s) values (%s)' % (item.table, keys, values)
        self.cursor.execute(sql, tuple(data.values()))
        self.db.commit()
        return item

三.图片下载管道

from scrapy.pipelines.images import ImagesPipeline
from scrapy.exceptions import DropItem
from scrapy import Request
import re


class ImagePipeline(ImagesPipeline):
    # 返回文件名及其相对路径
    # 'https://img.aitaotu.cc:8089/Pics/2020/0115/22/04.jpg'
    # '/Pics/2020/0115/22/04.jpg'
    def file_path(self, request, response=None, info=None):
        return re.search('(.*)8089(.*)', request.url).group(2)

    # 若下载失败，则抛出异常
    def item_completed(self, results, item, info):
        image_paths = [x['path'] for ok, x in results if ok]
        if not image_paths:
            raise DropItem('Image Downloaded Failed')
        return item

    # 设置请求头，下载图片
    def get_media_requests(self, item, info):
        headers = {
            "Referer": item['referer'],
            "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"
        }
        yield Request(item['image'], headers=headers)

四.其他文件

items.py

import scrapy


class AitaotuItem(scrapy.Item):
    collection = table = 'images'

    # 图片链接
    image = scrapy.Field()
    # 图片链接请求头关键参数，不然下载出现404
    referer = scrapy.Field()
    # 图片名称
    image_name = scrapy.Field()

settings.py

ROBOTSTXT_OBEY = False
DOWNLOAD_DELAY = 0.5

ITEM_PIPELINES = {
    'Aitaotu.pipelines.ImagePipeline': 300,
    'Aitaotu.pipelines.MongoPipeline': 301,
    'Aitaotu.pipelines.MysqlPipeline': 302,
}

# 图片管道配置
IMAGES_STORE = './images'

# mongodb配置
MONGO_URI = 'localhost'
MONGO_DB = 'aitaotu'

# msyql配置
MYSQL_HOST = 'localhost'
MYSQL_PORT = 3306
MYSQL_USER = 'root'
MYSQL_PASSWORD = '123456'
MYSQL_DATABASE = 'aitaotu'

五.Feed 导出

scrapy crawl aitaotu -o images.json
scrapy crawl aitaotu -o images.jsonlines
scrapy crawl aitaotu -o images.csv
scrapy crawl aitaotu -o images.xml

• 点赞
• 收藏
• 分享
• • 文章举报

Ares82219102 发布了3 篇原创文章 · 获赞 0 · 访问量 144 私信 关注