使用scrapy自带的邮件模块

在setting 配置

SMTP_SERVER = 'smtp.qq.com'
SMTP_PORT = 465
SMTP_OVER_SSL = True
SMTP_CONNECTION_TIMEOUT = 10
EMAIL_PASSWORD = 'XXX'  # 填写生成的授权码
EMAIL_SENDER = 'XXX@qq.com'
EMAIL_RECIPIENTS = [EMAIL_SENDER]
EMAIL_SUBJECT = 'Email from #scrapydweb'

在代码中引mail入库

MailSender是scrapy自带的一个发送邮件的库

from scrapy.mail import MailSender

监听任务和发邮件

from scrapy import signals
from scrapy.mail import MailSender
from scrapy.exceptions import NotConfigured
from twisted.internet import task

class StatsMailer():
    def __init__(self, stats, recipients, mail, interval=3600.0):
        # interval 设置半个小时执行下任务
        self.stats = stats
        self.node_id = get_node_id()
        self.interval = interval
        self.task = None
        self.stats = stats
        self.recipients = recipients

    @classmethod
    def from_crawler(cls, crawler):
        recipients = crawler.settings.getlist("STATSMAILER_RCPTS")
        if not recipients:
            raise NotConfigured
        mail = MailSender.from_settings(crawler.settings)
        o = cls(crawler.stats, recipients, mail)
        crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
        crawler.signals.connect(o.spider_closed, signal=signals.spider_closed)
        return o
          def spider_opened(self, spider):

        self.task = task.LoopingCall(self.send_email, spider)
        self.task.start(self.interval)

    def send_email(self, spider):
        body = ''    # 发送邮件的正文
        if body:
            return self.mail.send(self.recipients, "Scrapy stats for: %s" % spider.name, body)

    def spider_closed(self, spider, reason):
        if self.task and self.task.running:
            self.task.stop()

在扩展中引用

EXTENSIONS = {
            '路径.StatsMailer': 900
        }