Scrapy源码（2）——爬虫开始的地方

Usage examples:

$ scrapy crawl myspider
[ ... myspider starts crawling ... ]

$ scrapy runspider myspider.py
[ ... spider starts crawling ... ]

from scrapy import cmdline

cmdline.execute("scrapy crawl myspider".split())

def execute(argv=None, settings=None):
    if argv is None:
        argv = sys.argv

    # --- backwards compatibility for scrapy.conf.settings singleton ---
    if settings is None and 'scrapy.conf' in sys.modules:
        from scrapy import conf
        if hasattr(conf, 'settings'):
            settings = conf.settings
    # ------------------------------------------------------------------

    if settings is None:
        settings = get_project_settings()
        # set EDITOR from environment if available
        try:
            editor = os.environ['EDITOR']
        except KeyError: pass
        else:
            settings['EDITOR'] = editor
    check_deprecated_settings(settings)

    # --- backwards compatibility for scrapy.conf.settings singleton ---
    import warnings
    from scrapy.exceptions import ScrapyDeprecationWarning
    with warnings.catch_warnings():
        warnings.simplefilter("ignore", ScrapyDeprecationWarning)
        from scrapy import conf
        conf.settings = settings
    # ------------------------------------------------------------------

def get_project_settings():
    if ENVVAR not in os.environ:
        project = os.environ.get('SCRAPY_PROJECT', 'default')
        init_env(project)

def init_env(project='default', set_syspath=True):
    """Initialize environment to use command-line tool from inside a project
    dir. This sets the Scrapy settings module and modifies the Python path to
    be able to locate the project module.
    """
    cfg = get_config()
    if cfg.has_option('settings', project):
        os.environ['SCRAPY_SETTINGS_MODULE'] = cfg.get('settings', project)
    closest = closest_scrapy_cfg()
    if closest:
        projdir = os.path.dirname(closest)
        if set_syspath and projdir not in sys.path:
            sys.path.append(projdir)

    settings = Settings()
    settings_module_path = os.environ.get(ENVVAR)
    if settings_module_path:
        settings.setmodule(settings_module_path, priority='project')

    # XXX: remove this hack
    pickled_settings = os.environ.get("SCRAPY_PICKLED_SETTINGS_TO_OVERRIDE")
    if pickled_settings:
        settings.setdict(pickle.loads(pickled_settings), priority='project')

    # XXX: deprecate and remove this functionality
    env_overrides = {k[7:]: v for k, v in os.environ.items() if
                     k.startswith('SCRAPY_')}
    if env_overrides:
        settings.setdict(env_overrides, priority='project')

    return settings

    inproject = inside_project()
    cmds = _get_commands_dict(settings, inproject)
    cmdname = _pop_command_name(argv)
    parser = optparse.OptionParser(formatter=optparse.TitledHelpFormatter(), \
        conflict_handler='resolve')
    if not cmdname:
        _print_commands(settings, inproject)
        sys.exit(0)
    elif cmdname not in cmds:
        _print_unknown_command(settings, cmdname, inproject)
        sys.exit(2)

    cmd = cmds[cmdname]
    parser.usage = "scrapy %s %s" % (cmdname, cmd.syntax())
    parser.description = cmd.long_desc()
    settings.setdict(cmd.default_settings, priority='command')
    cmd.settings = settings
    cmd.add_options(parser)
    opts, args = parser.parse_args(args=argv[1:])
    _run_print_help(parser, cmd.process_options, args, opts)

    cmd.crawler_process = CrawlerProcess(settings)
    _run_print_help(parser, _run_command, cmd, args, opts)
    sys.exit(cmd.exitcode)

def _run_command(cmd, args, opts):
    if opts.profile:
        _run_command_profiled(cmd, args, opts)
    else:
        cmd.run(args, opts)

# Here’s an example showing how to run a single spider with it.

import scrapy
from scrapy.crawler import CrawlerProcess

class MySpider(scrapy.Spider):
    # Your spider definition
    ...

process = CrawlerProcess({
    'USER_AGENT': 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)'
})

process.crawl(MySpider)
process.start() # the script will block here until the crawling is finished

    """
    A class to run multiple scrapy crawlers in a process simultaneously.

    This class extends :class:`~scrapy.crawler.CrawlerRunner` by adding support
    for starting a Twisted `reactor`_ and handling shutdown signals, like the
    keyboard interrupt command Ctrl-C. It also configures top-level logging.

    This utility should be a better fit than
    :class:`~scrapy.crawler.CrawlerRunner` if you aren't running another
    Twisted `reactor`_ within your application.

    The CrawlerProcess object must be instantiated with a
    :class:`~scrapy.settings.Settings` object.

    :param install_root_handler: whether to install root logging handler
        (default: True)

    This class shouldn't be needed (since Scrapy is responsible of using it
    accordingly) unless writing scripts that manually handle the crawling
    process. See :ref:`run-from-script` for an example.
    """