数据采集 - 获取【一品威客】最新发布需求，并实时通知用户案例四

背景

有个朋友计划拓展业务渠道，准备在众包平台上接单，他的主营产品是微信小程序，因此他想第一时间收到客户发出的需求信息，然后第一时间联系客户，这样成交率才能够得到保障，否则单早都被其他同行接完了，他的黄花菜也就都凉了。

开发环境

开发语言 Python ，开发架构Scrapy，非 Python 莫属，数据采集的神器！
开发工具 PyCharm;

功能设计

实时通知：采用发邮件方式通知，将邮箱绑定到微信，实现实时通知的效果。
过滤模块：根据标题和内容双重过滤关键词，不符合要求的订单丢弃，符合要求的订单实时通知。
配置模块：采用json文件配置。

关键代码

采集模块

# -*- coding: utf-8 -*-
import time

import scrapy
from scrapy import Selector
from .. import common


class YpwktaskSpider(scrapy.Spider):
    name = 'ypwktask'
    allowed_domains = ['ypwk.com']
    start_urls = ['https://www.epwk.com/task/develop/']

    def parse(self, response):
        # pass
        # price = response.xpath('//h3[@class="a2"]/b/text()').getall()
        # name= response.xpath('//h3[@class="a2"]//@indus_pname').getall()
        # desc = response.xpath('//h3[@class="a2"]//@desc').getall()
        # url = response.xpath('//h3[@class="a2"]//@url').getall()
        nodes = response.xpath('//h3[@class="a2"]').getall()
        for node in nodes:
            # print(node)
            price = Selector(text=node).xpath('//b/text()').get().replace(u'\xa0', u' ')
            name = Selector(text=node).xpath('//@indus_pname').get().replace(u'\xa0', u' ')
            desc = Selector(text=node).xpath('//@desc').get().replace(u'\xa0', u' ')
            url = Selector(text=node).xpath('//@url').get()
            urgent = Selector(text=node).xpath('//span//@title ').get()
            if urgent is None:
                urgent = ''
            id = Selector(text=node).xpath('//@id ').get()

            print(name, price, desc, url, urgent, id)
            sended_id = common.read_taskid()
            if int(id) > sended_id:
                subject = "YPWK " + id + " " + name
                # content = price + "\n" + desc + "\n" + url + "\n" + urgent + "\n"
                content = "%s <p> %s <p> < a href=%s>%s</ a>  <p> %s" % (price, desc, url, url, urgent)
                if common.send_mail(subject, content):
                    common.write_taskid(id=int(id))
                    print("mail: send task <%s> sucess " % id)
                else:
                    print("mail: send task <%s> fail " % id)
            else:
                print("mail: task is already sended  <%s>" % id)
            time.sleep(3)

通知模块

 
def send_mail(subject, content):
    sender = u'xxxxx@qq.com'  # 发送人邮箱
    passwd = u'xxxxxx'  # 发送人邮箱授权码
    receivers = u'xxxxx@qq.com'  # 收件人邮箱
 
    # subject = u'一品威客 开发任务 ' #主题
    # content = u'这是我使用python smtplib模块和email模块自动发送的邮件'    #正文
    try:
        # msg = MIMEText(content, 'plain', 'utf-8')
        msg = MIMEText(content, 'html', 'utf-8')
        msg['Subject'] = subject
        msg['From'] = sender
        msg['TO'] = receivers
 
        s = smtplib.SMTP_SSL('smtp.qq.com', 465)
        s.set_debuglevel(1)
        s.login(sender, passwd)
        s.sendmail(sender, receivers, msg.as_string())
        return True
    except Exception as e:
        print(e)
        return False