scrapy save mysql or mongo, 和图片下载保存

Posted 2020-11-09 qukaige

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

# Define your item pipelines here
#
# Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import pymongo
import pymysql
from scrapy import Request
from scrapy.exceptions import DropItem
from scrapy.pipelines.images import ImagesPipeline


class Images360Pipeline(object):
    def process_item(self, item, spider):
        return item


# mongo db
class MongoPipeline(object):
    def __init__(self, mongo_url, mongo_db):
        self.mongo_url = mongo_url
        self.mongo_db = mongo_db

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            mongo_url=crawler.settings.get(‘MONGO_URL‘),
            mongo_db=crawler.settings.get(‘MONGO_DB‘)
        )

    def open_spider(self, spider):
        self.client = pymongo.MongoClient(self.mongo_url)
        self.db = self.client[self.mongo_db]

    def process_item(self, item, spider):
        self.db[item.collection].insert(dict(item))
        return item

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


# mysql
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())
        value = ‘,‘.join([‘%s‘] * len(data))
        sql = ‘insert into %s (%s) values (%s)‘ % (item.table, keys, value)
        self.cursor.execute(sql, tuple(data.values()))
        self.db.commit()
        return item


# 下载图片
class ImagePipeline(ImagesPipeline):
    def file_path(self, request, response=None, info=None):
        url = request.url
        file_name = url.split(‘/‘)[-1]
        return file_name

    # 如果图片下载失败,不进行保存数据库,IMAGES_STORE = ‘保存的文件名称如: ./images‘
    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

    def get_media_requests(self, item, info):
        yield Request(item[‘url‘])

settings.py配置

# 只列出部分代码,最先执行ImagePipeline

ITEM_PIPELINES = {
    ‘images360.pipelines.ImagePipeline‘: 300,
    ‘images360.pipelines.MongoPipeline‘: 301,
    ‘images360.pipelines.MysqlPipeline‘: 302,
}

MAX_PAGE = 50
MONGO_URL = ‘localhost‘
MONGO_DB = ‘images360‘
BOT_NAME = ‘images360‘
MYSQL_HOST = ‘localhost‘
MYSQL_DATABASE = ‘images360‘
MYSQL_USER = ‘root‘
MYSQL_PASSWORD = ‘123456‘
MYSQL_PORT = ‘3306‘
# 下载的图片保存路径
IMAGE_STORE = ‘./images‘

SPIDER_MODULES = [‘images360.spiders‘]
NEWSPIDER_MODULE = ‘images360.spiders‘

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = ‘images360 (+http://www.yourdomain.com)‘

# Obey robots.txt rules
ROBOTSTXT_OBEY = False