Spider代码

爬取新浪彩票双色球页面数据，只爬取期号、红球、篮球

class Shuangseqiu11Spider(scrapy.Spider):
    name = "shuangseqiu11"
    allowed_domains = ["sina.com.cn"]
    start_urls = ["https://view.lottery.sina.com.cn/lotto/pc_zst/index?lottoType=ssq&actionType=chzs&type=50&dpc=1"]

    def parse(self, response,**kwargs):
        cpdatas = response.xpath("//*[@id='cpdata']/tr")
        for cpdata in cpdatas:
            qihao = cpdata.xpath("./td[1]/text()").extract_first()
            hongse = cpdata.xpath("./td[@class='chartball01' or @class='chartball20']/text()").extract()
            lanse = cpdata.xpath("./td[@class='chartball02']/text()").extract_first()
            if not hongse:
                continue

            dict = {
                "qihao":qihao,
                "hongse":hongse,
                "lanse":lanse
            }
            yield dict

CSV文件写入

在《爬虫框架Scrapy初使用_爬取4399游戏页面数据》中通过写入一条数据打开一次文件，我们希望的是, 能不能打开一个文件, 然后就用这一个文件句柄来完成数据的保存. 答案是可以的. 我们可以在pipeline中创建两个方法, 一个是open_spider(), 另一个是close_spider(). 看名字也能明白其含义:

open_spider(), 在爬虫开始的时候执行一次
close_spider(), 在爬虫结束的时候执行一次
整体代码如下：

class ShuangseqiuPipeline:
    def open_spider(self,spider):
        print("开始了")
        self.f = open('data2.csv',mode='a',encoding="UTF-8")
    def close_spider(self,spider):
        print("结束了")
        self.f.close()
    def process_item(self, item, spider):
        self.f.write(f"{item['qihao']},{'_'.join(item['hongse'])},{item['lanse']}\n")
        return item

MYSQL文件写入

在setting配置中添加Mysql数据库信息

setting.py
# MYSQL配置信息
MYSQL_CONFIG = {
   "host": "localhost",
   "port": 3306,
   "user": "root",
   "password": "test123456",
   "database": "spider",
}

#pipeline.py
from caipiao.settings import MYSQL_CONFIG as mysql
import pymysql

class CaipiaoMySQLPipeline:

    def open_spider(self, spider):
        self.conn = pymysql.connect(host=mysql["host"], port=mysql["port"], user=mysql["user"], password=mysql["password"], database=mysql["database"])

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

    def process_item(self, item, spider):
        # 写入文件
        try:
            cursor = self.conn.cursor()
            sql = "insert into caipiao(qihao, red, blue) values(%s, %s, %s)"
            red = ",".join(item['red_ball'])
            blue = ",".join(item['blue_ball'])
            cursor.execute(sql, (item['qihao'], red, blue))
            self.conn.commit()
            spider.logger.info(f"保存数据{item}")
        except Exception as e:
            self.conn.rollback()
            spider.logger.error(f"保存数据库失败!", e, f"数据是: {item}")  # 记录错误日志
        return item

MongoDB文件写入

在setting中添加mongodb配置

MONGO_CONFIG = {
   "host": "localhost",
   "port": 27017,
   #'has_user': True,
   #'user': "python_admin",
   #"password": "123456",
   "db": "python"
}

from caipiao.settings import MONGO_CONFIG as mongo
import pymongo

class CaipiaoMongoDBPipeline:
    def open_spider(self, spider):
        client = pymongo.MongoClient(host=mongo['host'],
                                     port=mongo['port'])
        db = client[mongo['db']]
        #if mongo['has_user']:
        #    db.authenticate(mongo['user'], mongo['password'])
        self.client = client  #  你们那里不用这么麻烦. 
        self.collection = db['caipiao']

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

    def process_item(self, item, spider):
        self.collection.insert({"qihao": item['qihao'], 'red': item["red_ball"], 'blue': item['blue_ball']})
        return item

同时存储数据

在setting配置文件中同时添加三个管道

ITEM_PIPELINES = {
    # 三个管道可以共存~
   'caipiao.pipelines.CaipiaoFilePipeline': 300,
   'caipiao.pipelines.CaipiaoMySQLPipeline': 301,
   'caipiao.pipelines.CaipiaoMongoDBPipeline': 302,
}