File: crawler.py

package info (click to toggle)
python-scrapy 1.5.1-1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, buster, sid
  • size: 4,308 kB
  • sloc: python: 25,583; xml: 199; makefile: 95; sh: 33
file content (336 lines) | stat: -rw-r--r-- 12,863 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
import six
import signal
import logging
import warnings

import sys
from twisted.internet import reactor, defer
from zope.interface.verify import verifyClass, DoesNotImplement

from scrapy.core.engine import ExecutionEngine
from scrapy.resolver import CachingThreadedResolver
from scrapy.interfaces import ISpiderLoader
from scrapy.extension import ExtensionManager
from scrapy.settings import overridden_settings, Settings
from scrapy.signalmanager import SignalManager
from scrapy.exceptions import ScrapyDeprecationWarning
from scrapy.utils.ossignal import install_shutdown_handlers, signal_names
from scrapy.utils.misc import load_object
from scrapy.utils.log import (
    LogCounterHandler, configure_logging, log_scrapy_info,
    get_scrapy_root_handler, install_scrapy_root_handler)
from scrapy import signals

logger = logging.getLogger(__name__)


class Crawler(object):

    def __init__(self, spidercls, settings=None):
        if isinstance(settings, dict) or settings is None:
            settings = Settings(settings)

        self.spidercls = spidercls
        self.settings = settings.copy()
        self.spidercls.update_settings(self.settings)

        d = dict(overridden_settings(self.settings))
        logger.info("Overridden settings: %(settings)r", {'settings': d})

        self.signals = SignalManager(self)
        self.stats = load_object(self.settings['STATS_CLASS'])(self)

        handler = LogCounterHandler(self, level=self.settings.get('LOG_LEVEL'))
        logging.root.addHandler(handler)
        if get_scrapy_root_handler() is not None:
            # scrapy root handler already installed: update it with new settings
            install_scrapy_root_handler(self.settings)
        # lambda is assigned to Crawler attribute because this way it is not
        # garbage collected after leaving __init__ scope
        self.__remove_handler = lambda: logging.root.removeHandler(handler)
        self.signals.connect(self.__remove_handler, signals.engine_stopped)

        lf_cls = load_object(self.settings['LOG_FORMATTER'])
        self.logformatter = lf_cls.from_crawler(self)
        self.extensions = ExtensionManager.from_crawler(self)

        self.settings.freeze()
        self.crawling = False
        self.spider = None
        self.engine = None

    @property
    def spiders(self):
        if not hasattr(self, '_spiders'):
            warnings.warn("Crawler.spiders is deprecated, use "
                          "CrawlerRunner.spider_loader or instantiate "
                          "scrapy.spiderloader.SpiderLoader with your "
                          "settings.",
                          category=ScrapyDeprecationWarning, stacklevel=2)
            self._spiders = _get_spider_loader(self.settings.frozencopy())
        return self._spiders

    @defer.inlineCallbacks
    def crawl(self, *args, **kwargs):
        assert not self.crawling, "Crawling already taking place"
        self.crawling = True

        try:
            self.spider = self._create_spider(*args, **kwargs)
            self.engine = self._create_engine()
            start_requests = iter(self.spider.start_requests())
            yield self.engine.open_spider(self.spider, start_requests)
            yield defer.maybeDeferred(self.engine.start)
        except Exception:
            # In Python 2 reraising an exception after yield discards
            # the original traceback (see https://bugs.python.org/issue7563),
            # so sys.exc_info() workaround is used.
            # This workaround also works in Python 3, but it is not needed,
            # and it is slower, so in Python 3 we use native `raise`.
            if six.PY2:
                exc_info = sys.exc_info()

            self.crawling = False
            if self.engine is not None:
                yield self.engine.close()

            if six.PY2:
                six.reraise(*exc_info)
            raise

    def _create_spider(self, *args, **kwargs):
        return self.spidercls.from_crawler(self, *args, **kwargs)

    def _create_engine(self):
        return ExecutionEngine(self, lambda _: self.stop())

    @defer.inlineCallbacks
    def stop(self):
        if self.crawling:
            self.crawling = False
            yield defer.maybeDeferred(self.engine.stop)


class CrawlerRunner(object):
    """
    This is a convenient helper class that keeps track of, manages and runs
    crawlers inside an already setup Twisted `reactor`_.

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

    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.
    """

    crawlers = property(
        lambda self: self._crawlers,
        doc="Set of :class:`crawlers <scrapy.crawler.Crawler>` started by "
            ":meth:`crawl` and managed by this class."
    )

    def __init__(self, settings=None):
        if isinstance(settings, dict) or settings is None:
            settings = Settings(settings)
        self.settings = settings
        self.spider_loader = _get_spider_loader(settings)
        self._crawlers = set()
        self._active = set()

    @property
    def spiders(self):
        warnings.warn("CrawlerRunner.spiders attribute is renamed to "
                      "CrawlerRunner.spider_loader.",
                      category=ScrapyDeprecationWarning, stacklevel=2)
        return self.spider_loader

    def crawl(self, crawler_or_spidercls, *args, **kwargs):
        """
        Run a crawler with the provided arguments.

        It will call the given Crawler's :meth:`~Crawler.crawl` method, while
        keeping track of it so it can be stopped later.

        If `crawler_or_spidercls` isn't a :class:`~scrapy.crawler.Crawler`
        instance, this method will try to create one using this parameter as
        the spider class given to it.

        Returns a deferred that is fired when the crawling is finished.

        :param crawler_or_spidercls: already created crawler, or a spider class
            or spider's name inside the project to create it
        :type crawler_or_spidercls: :class:`~scrapy.crawler.Crawler` instance,
            :class:`~scrapy.spiders.Spider` subclass or string

        :param list args: arguments to initialize the spider

        :param dict kwargs: keyword arguments to initialize the spider
        """
        crawler = self.create_crawler(crawler_or_spidercls)
        return self._crawl(crawler, *args, **kwargs)

    def _crawl(self, crawler, *args, **kwargs):
        self.crawlers.add(crawler)
        d = crawler.crawl(*args, **kwargs)
        self._active.add(d)

        def _done(result):
            self.crawlers.discard(crawler)
            self._active.discard(d)
            return result

        return d.addBoth(_done)

    def create_crawler(self, crawler_or_spidercls):
        """
        Return a :class:`~scrapy.crawler.Crawler` object.

        * If `crawler_or_spidercls` is a Crawler, it is returned as-is.
        * If `crawler_or_spidercls` is a Spider subclass, a new Crawler
          is constructed for it.
        * If `crawler_or_spidercls` is a string, this function finds
          a spider with this name in a Scrapy project (using spider loader),
          then creates a Crawler instance for it.
        """
        if isinstance(crawler_or_spidercls, Crawler):
            return crawler_or_spidercls
        return self._create_crawler(crawler_or_spidercls)

    def _create_crawler(self, spidercls):
        if isinstance(spidercls, six.string_types):
            spidercls = self.spider_loader.load(spidercls)
        return Crawler(spidercls, self.settings)

    def stop(self):
        """
        Stops simultaneously all the crawling jobs taking place.

        Returns a deferred that is fired when they all have ended.
        """
        return defer.DeferredList([c.stop() for c in list(self.crawlers)])

    @defer.inlineCallbacks
    def join(self):
        """
        join()

        Returns a deferred that is fired when all managed :attr:`crawlers` have
        completed their executions.
        """
        while self._active:
            yield defer.DeferredList(self._active)


class CrawlerProcess(CrawlerRunner):
    """
    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.
    """

    def __init__(self, settings=None, install_root_handler=True):
        super(CrawlerProcess, self).__init__(settings)
        install_shutdown_handlers(self._signal_shutdown)
        configure_logging(self.settings, install_root_handler)
        log_scrapy_info(self.settings)

    def _signal_shutdown(self, signum, _):
        install_shutdown_handlers(self._signal_kill)
        signame = signal_names[signum]
        logger.info("Received %(signame)s, shutting down gracefully. Send again to force ",
                    {'signame': signame})
        reactor.callFromThread(self._graceful_stop_reactor)

    def _signal_kill(self, signum, _):
        install_shutdown_handlers(signal.SIG_IGN)
        signame = signal_names[signum]
        logger.info('Received %(signame)s twice, forcing unclean shutdown',
                    {'signame': signame})
        reactor.callFromThread(self._stop_reactor)

    def start(self, stop_after_crawl=True):
        """
        This method starts a Twisted `reactor`_, adjusts its pool size to
        :setting:`REACTOR_THREADPOOL_MAXSIZE`, and installs a DNS cache based
        on :setting:`DNSCACHE_ENABLED` and :setting:`DNSCACHE_SIZE`.

        If `stop_after_crawl` is True, the reactor will be stopped after all
        crawlers have finished, using :meth:`join`.

        :param boolean stop_after_crawl: stop or not the reactor when all
            crawlers have finished
        """
        if stop_after_crawl:
            d = self.join()
            # Don't start the reactor if the deferreds are already fired
            if d.called:
                return
            d.addBoth(self._stop_reactor)

        reactor.installResolver(self._get_dns_resolver())
        tp = reactor.getThreadPool()
        tp.adjustPoolsize(maxthreads=self.settings.getint('REACTOR_THREADPOOL_MAXSIZE'))
        reactor.addSystemEventTrigger('before', 'shutdown', self.stop)
        reactor.run(installSignalHandlers=False)  # blocking call

    def _get_dns_resolver(self):
        if self.settings.getbool('DNSCACHE_ENABLED'):
            cache_size = self.settings.getint('DNSCACHE_SIZE')
        else:
            cache_size = 0
        return CachingThreadedResolver(
            reactor=reactor,
            cache_size=cache_size,
            timeout=self.settings.getfloat('DNS_TIMEOUT')
        )

    def _graceful_stop_reactor(self):
        d = self.stop()
        d.addBoth(self._stop_reactor)
        return d

    def _stop_reactor(self, _=None):
        try:
            reactor.stop()
        except RuntimeError:  # raised if already stopped or in shutdown stage
            pass


def _get_spider_loader(settings):
    """ Get SpiderLoader instance from settings """
    if settings.get('SPIDER_MANAGER_CLASS'):
        warnings.warn(
            'SPIDER_MANAGER_CLASS option is deprecated. '
            'Please use SPIDER_LOADER_CLASS.',
            category=ScrapyDeprecationWarning, stacklevel=2
        )
    cls_path = settings.get('SPIDER_MANAGER_CLASS',
                            settings.get('SPIDER_LOADER_CLASS'))
    loader_cls = load_object(cls_path)
    try:
        verifyClass(ISpiderLoader, loader_cls)
    except DoesNotImplement:
        warnings.warn(
            'SPIDER_LOADER_CLASS (previously named SPIDER_MANAGER_CLASS) does '
            'not fully implement scrapy.interfaces.ISpiderLoader interface. '
            'Please add all missing methods to avoid unexpected runtime errors.',
            category=ScrapyDeprecationWarning, stacklevel=2
        )
    return loader_cls.from_settings(settings.frozencopy())