python爬虫之scrapy的pipeline的使用

Posted 2020-10-15 Charles.L

scrapy的pipeline是一个非常重要的模块，主要作用是将return的items写入到数据库、文件等持久化模块，下面我们就简单的了解一下pipelines的用法。

案例一：

　　

items池

class ZhihuuserItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    id = scrapy.Field()
    name = scrapy.Field()
    avatar_url = scrapy.Field()
    headline = scrapy.Field()
    description = scrapy.Field()
    url = scrapy.Field()
    url_token = scrapy.Field()
    gender = scrapy.Field()
    cover_url = scrapy.Field()
    type = scrapy.Field()
    badge = scrapy.Field()

    answer_count = scrapy.Field()
    articles_count = scrapy.Field()
    commercial_question = scrapy.Field()
    favorite_count = scrapy.Field()
    favorited_count = scrapy.Field()
    follower_count = scrapy.Field()
    following_columns_count = scrapy.Field()
    following_count = scrapy.Field()
    pins_count = scrapy.Field()
    question_count = scrapy.Field()
    thank_from_count = scrapy.Field()
    thank_to_count = scrapy.Field()
    thanked_count = scrapy.Field()
    vote_from_count = scrapy.Field()
    vote_to_count = scrapy.Field()
    voteup_count = scrapy.Field()
    following_favlists_count = scrapy.Field()
    following_question_count = scrapy.Field()
    following_topic_count = scrapy.Field()
    marked_answers_count = scrapy.Field()
    mutual_followees_count = scrapy.Field()
    participated_live_count = scrapy.Field()

    locations = scrapy.Field()
    educations = scrapy.Field()
    employments = scrapy.Field()

items

 写入MongoDB数据库的基本配置

#配置MongoDB数据库的连接信息
MONGO_URL = \'172.16.5.239\'
MONGO_PORT = 27017
MONGO_DB = \'zhihuuser\'

#参数等于False，就等于告诉你这个网站你想取什么就取什么，不会读取每个网站的根目录下的禁止爬取列表(例如：www.baidu.com/robots.txt）
ROBOTSTXT_OBEY = False


执行pipelines下的写入操作
ITEM_PIPELINES = {
   \'zhihuuser.pipelines.MongoDBPipeline\': 300,
}

settings.py

 

pipelines.py：
　　1、首先我们要从settings文件中读取数据的地址、端口、数据库名称（没有会自动创建）。
　　2、拿到数据库的基本信息后进行连接。
　　3、将数据写入数据库
　　4、关闭数据库
　　注意：只有打开和关闭是只执行一次，而写入操作会根据具体的写入次数而定。

import pymongo

class MongoDBPipeline(object):
    """
    1、连接数据库操作
    """
    def __init__(self,mongourl,mongoport,mongodb):
        \'\'\'
        初始化mongodb数据的url、端口号、数据库名称
        :param mongourl:
        :param mongoport:
        :param mongodb:
        \'\'\'
        self.mongourl = mongourl
        self.mongoport = mongoport
        self.mongodb = mongodb

    @classmethod
    def from_crawler(cls,crawler):
        """
        1、读取settings里面的mongodb数据的url、port、DB。
        :param crawler:
        :return:
        """
        return cls(
            mongourl = crawler.settings.get("MONGO_URL"),
            mongoport = crawler.settings.get("MONGO_PORT"),
            mongodb = crawler.settings.get("MONGO_DB")
        )

    def open_spider(self,spider):
        \'\'\'
        1、连接mongodb数据
        :param spider:
        :return:
        \'\'\'
        self.client = pymongo.MongoClient(self.mongourl,self.mongoport)
        self.db = self.client[self.mongodb]

    def process_item(self,item,spider):
        \'\'\'
        1、将数据写入数据库
        :param item:
        :param spider:
        :return:
        \'\'\'
        name = item.__class__.__name__
        # self.db[name].insert(dict(item))
        self.db[\'user\'].update({\'url_token\':item[\'url_token\']},{\'$set\':item},True)
        return item

    def close_spider(self,spider):
        \'\'\'
        1、关闭数据库连接
        :param spider:
        :return:
        \'\'\'
        self.client.close()