scrapy自定义Pipline

第一个事mysql 同步Pipline，适用爬虫量小

导入文件
import MySQLdb
import MySQLdb.cursors


class MysqlPipeline(object):
    #采用同步的机制写入mysql
    def __init__(self):
        self.conn = MySQLdb.connect('192.168.0.106', 'root', 'root', 'article_spider', charset="utf8", use_unicode=True)
        self.cursor = self.conn.cursor()

    def process_item(self, item, spider):
        insert_sql = """
            insert into jobbole_article(title, url, create_date, fav_nums)
            VALUES (%s, %s, %s, %s)
        """
        self.cursor.execute(insert_sql, (item["title"], item["url"], item["create_date"], item["fav_nums"]))
        self.conn.commit()

异步mysql 的pipline, 适用爬虫量大。

导入的文件
from twisted.enterprise import adbapi


class MysqlTwistedPipline(object):
    def __init__(self, dbpool):
        self.dbpool = dbpool

    @classmethod
    def from_settings(cls, settings):
        dbparms = dict(
            host = settings["MYSQL_HOST"],
            db = settings["MYSQL_DBNAME"],
            user = settings["MYSQL_USER"],
            passwd = settings["MYSQL_PASSWORD"],
            charset='utf8',
            cursorclass=MySQLdb.cursors.DictCursor,
            use_unicode=True,
        )
        dbpool = adbapi.ConnectionPool("MySQLdb", **dbparms)

        return cls(dbpool)

    def process_item(self, item, spider):
        #使用twisted将mysql插入变成异步执行
        query = self.dbpool.runInteraction(self.do_insert, item)
        query.addErrback(self.handle_error, item, spider) #处理异常

    def handle_error(self, failure, item, spider):
        # 处理异步插入的异常
        print (failure)

    def do_insert(self, cursor, item):
        #执行具体的插入
        #根据不同的item 构建不同的sql语句并插入到mysql中
        insert_sql, params = item.get_insert_sql()
        print (insert_sql, params)
        cursor.execute(insert_sql, params)

自定义下载图片

导入文件
from scrapy.pipelines.images import ImagesPipeline

class ArticleImagePipeline(ImagesPipeline):
    def item_completed(self, results, item, info):
        if "front_image_url" in item:
            for ok, value in results:
                image_file_path = value["path"]
            item["front_image_path"] = image_file_path

        return item

最后还有在seting 文件里设置,

   如果需要下载的图片路径要入数据库, 就要权重小与入数据库权重
  'ArticleSpider.pipelines.ArticleImagePipeline': 2,


得别要注意front_image_url  跟item的字段一样啊。
IMAGES_URLS_FIELD = "front_image_url"
project_dir = os.path.abspath(os.path.dirname(__file__))
IMAGES_STORE = os.path.join(project_dir, 'images')