16Python爬虫---Scrapy多开技能

在Scrapy项目中创建一个文件夹存放我们自己编写的mycrawl文件，然后创建3个爬虫myspd1,myspd2,myspd3
项目结构

下面为mycrawl.py源码

import os
from scrapy.commands import ScrapyCommand
from scrapy.utils.conf import arglist_to_dict
from scrapy.utils.python import without_none_values
from scrapy.exceptions import UsageError


class Command(ScrapyCommand):

    requires_project = True

    def syntax(self):
        return "[options] <spider>"

    def short_desc(self):
        return "Run a spider"

    def add_options(self, parser):
        ScrapyCommand.add_options(self, parser)
        parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE",
                          help="set spider argument (may be repeated)")
        parser.add_option("-o", "--output", metavar="FILE",
                          help="dump scraped items into FILE (use - for stdout)")
        parser.add_option("-t", "--output-format", metavar="FORMAT",
                          help="format to use for dumping items with -o")

    def process_options(self, args, opts):
        ScrapyCommand.process_options(self, args, opts)
        try:
            opts.spargs = arglist_to_dict(opts.spargs)
        except ValueError:
            raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False)
        if opts.output:
            if opts.output == '-':
                self.settings.set('FEED_URI', 'stdout:', priority='cmdline')
            else:
                self.settings.set('FEED_URI', opts.output, priority='cmdline')
            feed_exporters = without_none_values(
                self.settings.getwithbase('FEED_EXPORTERS'))
            valid_output_formats = feed_exporters.keys()
            if not opts.output_format:
                opts.output_format = os.path.splitext(opts.output)[1].replace(".", "")
            if opts.output_format not in valid_output_formats:
                raise UsageError("Unrecognized output format '%s', set one"
                                 " using the '-t' switch or as a file extension"
                                 " from the supported list %s" % (opts.output_format,
                                                                  tuple(valid_output_formats)))
            self.settings.set('FEED_FORMAT', opts.output_format, priority='cmdline')
# 主要修改这里
    def run(self, args, opts):
        # 获取爬虫列表
        spd_loader_list = self.crawler_process.spider_loader.list()
        # 遍历爬虫
        for spname in spd_loader_list or args:
            self.crawler_process.crawl(spname, **opts.spargs)
            print("此时启动的爬虫为："+spname)
        self.crawler_process.start()

修改完成后在settings.py中进行配置格式为”COMMANDS_MODULE=’项目核心目录.自定义命令源码目录’”，具体命令如下：
COMMANDS_MODULE = 'mymultispd.mycmd'
，随后进入该项目所在目录，并用scrapy -h命令查看，出现如下信息：

此时已经可以看到自定义命令mycrawl了。

---

然后通过命令启动所有爬虫文件

D:\PycharmProjects\crawler\day07_Scarpy\mymultispd\mymultispd>scrapy mycrawl --nolog
此时启动的爬虫为：myspd1
此时启动的爬虫为：myspd2
此时启动的爬虫为：myspd3

此时已经通过自定义的mycrawl命令同事启动了爬虫文件myspd1、myspd2、myspd3。