使用官方组件下载图片，保存到MySQL数据库，保存到MongoDB数据库

需要学习的地方，使用官方组件下载图片的用法，保存item到MySQL数据库

需要提前创建好MySQL数据库，根据item.py文件中的字段信息创建相应的数据表

1.items.py文件

from scrapy import Item,Field

class Images360Item(Item):
    # MongoDB数据库的表名和MySQL数据库的表名
    collection = table = 'images'
    id = Field()
    url = Field()
    title = Field()
    thumb = Field()

2.settings.py文件

ITEM_PIPELINES = {
   'images360.pipelines.ImagesPipeline': 300,
   'images360.pipelines.MongoPipeline': 301,
   'images360.pipelines.MySQLPipeline': 302,
}

# MongoDB数据库参数
MONGO_URI = '127.0.0.1'
MONGO_DATABASE = 'images360'

# 图片保存路径
IMAGES_STORE = 'D:\\images360\\images'

# MySQL数据库参数
MYSQL_HOST = '127.0.0.1'
MYSQL_DATABASE = 'images360'
MYSQL_USER = 'root'
MYSQL_PASSWORD = 'root'
MYSQL_PORT = 3306

 

3.pipeline.py文件

import pymongo
import pymysql
from scrapy import Request
from scrapy.exceptions import DropItem
from scrapy.pipelines.images import ImagesPipeline


# 下载项目图片
class ImagesPipeline(ImagesPipeline):
    def file_path(self, request, response=None, info=None):
        url = request.url
        filename = url.split('/')[-1]
        return filename

    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'])

# 保存到MongoDB数据库
class MongoPipeline(object):
    # 数据表名
    collection_name = 'scrapy_items'

    def __init__(self, mongo_uri, mongo_db):
        self.mongo_uri = mongo_uri
        self.mongo_db = mongo_db

    @classmethod
    # 从settings.py文件中获取参数
    def from_crawler(cls, crawler):
        return cls(
            mongo_uri=crawler.settings.get('MONGO_URI'),
            mongo_db=crawler.settings.get('MONGO_DATABASE', 'items')  # 数据库名
        )

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

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

    def process_item(self, item, spider):
        self.db[item.collection].insert_one(dict(item))  # 从items.py文件中获取表名
        return item


# 保存数据到MySQL数据库
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