def __init__(self, spidercls, settings):
if isinstance(settings, dict):
settings = Settings(settings)
self.spidercls = spidercls
self.settings = settings.copy()
self.signals = SignalManager(self)
self.stats = load_object(self.settings['STATS_CLASS'])(self)
handler = LogCounterHandler(self, level=settings.get('LOG_LEVEL'))
logging.root.addHandler(handler)
self.signals.connect(lambda: logging.root.removeHandler(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.spidercls.update_settings(self.settings)
self.settings.freeze()
self.crawling = False
self.spider = None
self.engine = None
def create_root(config):
from scrapy import log
from scrapy.settings import Settings
from slyd.crawlerspec import (CrawlerSpecManager,
create_crawler_spec_resource)
from slyd.bot import create_bot_resource
import slyd.settings
from slyd.projects import ProjectsResource
root = Resource()
root.putChild("static", File(config['docroot']))
crawler_settings = Settings()
crawler_settings.setmodule(slyd.settings)
spec_manager = CrawlerSpecManager(crawler_settings)
# add project management at /projects
projects = ProjectsResource(crawler_settings)
root.putChild('projects', projects)
# add crawler at /projects/PROJECT_ID/bot
log.msg("Slybot specs loading from %s/[PROJECT]" % spec_manager.basedir,
level=log.DEBUG)
projects.putChild("bot", create_bot_resource(spec_manager))
# add spec at /projects/PROJECT_ID/spec
spec = create_crawler_spec_resource(spec_manager)
projects.putChild("spec", spec)
return root
def get_fetch(log=False):
settings = Settings()
settings.set('LOG_ENABLED', log)
crawler_process = CrawlerProcess(settings)
crawler = crawler_process.create_crawler()
crawler_process.start_crawling()
t = Thread(target=crawler_process.start_reactor)
t.daemon = True
t.start()
shell = Shell(crawler)
shell.code = 'adsf'
import threading
lock = threading.Lock()
def fetch(url_or_request):
lock.acquire()
try:
shell.fetch(url_or_request)
response = shell.vars.get('response')
return response
finally:
lock.release()
return fetch
def test_from_settings_constructs_middleware_with_the_specified_settings():
settings = Settings()
settings.set('HTML_STORAGE', {'test': 'settings'})
downloader = HtmlStorageMiddleware.from_settings(settings)
assert_that(downloader.settings, is_({'test': 'settings'}))
def make_downloader(save_html_on_codes=[]):
settings = Settings()
settings.set('HTML_STORAGE', {
'gzip_output': True,
'save_html_on_codes': save_html_on_codes
})
return HtmlStorageMiddleware(settings)
def get_project_settings():
scrapy_module = "uris.urispider.settings"
settings = Settings()
settings.setmodule(scrapy_module)
return settings
def create_spec_manager(projects_dir=None):
"""Create a CrawlerSpecManager configured to use test settings"""
crawler_settings = ScrapySettings()
crawler_settings.setmodule(test_settings)
projects_dir = projects_dir or test_settings.SPEC_DATA_DIR
test_settings.SPEC_FACTORY['PARAMS']['location'] = projects_dir
return SpecManager(crawler_settings)
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)
self.signals = SignalManager(self)
self.stats = load_object(self.settings['STATS_CLASS'])(self)
handler = LogCounterHandler(self, level=settings.get('LOG_LEVEL'))
logging.root.addHandler(handler)
# 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
def test_autopromote_dicts(self):
settings = Settings()
mydict = settings.get('TEST_DICT')
self.assertIsInstance(mydict, BaseSettings)
self.assertIn('key', mydict)
self.assertEqual(mydict['key'], 'val')
self.assertEqual(mydict.getpriority('key'), 0)
def test_getdict_autodegrade_basesettings(self):
settings = Settings()
mydict = settings.getdict('TEST_DICT')
self.assertIsInstance(mydict, dict)
self.assertEqual(len(mydict), 1)
self.assertIn('key', mydict)
self.assertEqual(mydict['key'], 'val')
class FilesPipelineTestCaseCustomSettings(unittest.TestCase):
def setUp(self):
self.tempdir = mkdtemp()
self.pipeline = FilesPipeline(self.tempdir)
self.default_settings = Settings()
def tearDown(self):
rmtree(self.tempdir)
def test_expires(self):
another_pipeline = FilesPipeline.from_settings(Settings({'FILES_STORE': self.tempdir,
'FILES_EXPIRES': 42}))
self.assertEqual(self.pipeline.expires, self.default_settings.getint('FILES_EXPIRES'))
self.assertEqual(another_pipeline.expires, 42)
def test_files_urls_field(self):
another_pipeline = FilesPipeline.from_settings(Settings({'FILES_STORE': self.tempdir,
'FILES_URLS_FIELD': 'funny_field'}))
self.assertEqual(self.pipeline.files_urls_field, self.default_settings.get('FILES_URLS_FIELD'))
self.assertEqual(another_pipeline.files_urls_field, 'funny_field')
def test_files_result_field(self):
another_pipeline = FilesPipeline.from_settings(Settings({'FILES_STORE': self.tempdir,
'FILES_RESULT_FIELD': 'funny_field'}))
self.assertEqual(self.pipeline.files_result_field, self.default_settings.get('FILES_RESULT_FIELD'))
self.assertEqual(another_pipeline.files_result_field, 'funny_field')
def __init__(self, store_uri, download_func=None, settings=None):
if not store_uri:
raise NotConfigured
if isinstance(settings, dict) or settings is None:
settings = Settings(settings)
cls_name = "FilesPipeline"
self.store = self._get_store(store_uri)
resolve = functools.partial(self._key_for_pipe,
base_class_name=cls_name,
settings=settings)
self.expires = settings.getint(
resolve('FILES_EXPIRES'), self.EXPIRES
)
if not hasattr(self, "FILES_URLS_FIELD"):
self.FILES_URLS_FIELD = self.DEFAULT_FILES_URLS_FIELD
if not hasattr(self, "FILES_RESULT_FIELD"):
self.FILES_RESULT_FIELD = self.DEFAULT_FILES_RESULT_FIELD
self.files_urls_field = settings.get(
resolve('FILES_URLS_FIELD'), self.FILES_URLS_FIELD
)
self.files_result_field = settings.get(
resolve('FILES_RESULT_FIELD'), self.FILES_RESULT_FIELD
)
super(FilesPipeline, self).__init__(download_func=download_func)
def _crawl(self):
settings = Settings()
settings.set('ITEM_PIPELINES', {
'app.pipelines.JsonWriterPipeline': 300
})
self.process = CrawlerProcess(settings)
self.process.crawl(self, self.name, self.start_urls)
self.process.start()
def test_contructor_sets_default_settings_values_when_no_settings_are_specified(
setting_name, expected):
settings = Settings()
settings.set('HTML_STORAGE', {})
downloader = HtmlStorageMiddleware(settings)
assert_that(downloader.__dict__[setting_name], is_(expected))
def __init__(self, spider):
Process.__init__(self)
setting = Settings()
setting.setmodule(s)
self.crawler = Crawler(setting)
self.crawler.configure()
self.crawler.signals.connect(reactor.stop, signal=signals.spider_closed)
self.spider = spider
def __init__(self, settings):
if isinstance(settings, dict):
settings = Settings(settings)
self.settings = settings
smcls = load_object(settings['SPIDER_MANAGER_CLASS'])
verifyClass(ISpiderManager, smcls)
self.spiders = smcls.from_settings(settings.frozencopy())
self.crawlers = set()
self._active = set()
def runSpider(self, spider):
configure_logging({'LOG_FORMAT': '%(asctime)s [%(name)s] %(levelname)s: %(message)s'})
settings = Settings()
settings.set('FEED_URI', 'output.json')
settings.set('FEED_FORMAT', 'json')
runner = CrawlerRunner(settings)
dfd = runner.crawl(spider)
dfd.addBoth(lambda _: reactor.stop())
def __init__(self):
sets = Settings()
sets.setmodule(settings, priority='project')
connection = pymongo.MongoClient(
sets['MONGODB_SERVER'],
sets['MONGODB_PORT']
)
db = connection[sets['MONGODB_DB']]
self.collection = db[sets['MONGODB_COLLECTION']]
def create_root(config, settings_module):
from scrapy.settings import Settings
from .specmanager import SpecManager
from .authmanager import AuthManager
from .projectspec import create_project_resource
from slyd.bot import create_bot_resource
from slyd.projects import create_projects_manager_resource
from slyd.splash.ferry import (FerryServerProtocol, FerryServerFactory,
create_ferry_resource)
from slyd.splash.proxy import ProxyResource
root = Resource()
static = Resource()
for file_name in listdir(config['docroot']):
file_path = join(config['docroot'], file_name)
if isfile(file_path):
static.putChild(file_name, File(file_path))
static.putChild('main.html', File(join(config['docroot'], 'index.html')))
root.putChild('static', static)
root.putChild('assets', File(join(config['docroot'], 'assets')))
root.putChild('fonts', File(join(config['docroot'], 'assets', 'fonts')))
root.putChild('', File(join(config['docroot'], 'index.html')))
settings = Settings()
settings.setmodule(settings_module)
spec_manager = SpecManager(settings)
# add server capabilities at /server_capabilities
capabilities = Capabilities(spec_manager)
root.putChild('server_capabilities', capabilities)
# add projects manager at /projects
projects = create_projects_manager_resource(spec_manager)
root.putChild('projects', projects)
# add crawler at /projects/PROJECT_ID/bot
projects.putChild('bot', create_bot_resource(spec_manager))
# add project spec at /projects/PROJECT_ID/spec
spec = create_project_resource(spec_manager)
projects.putChild('spec', spec)
# add websockets for communicating with splash
factory = FerryServerFactory("ws://127.0.0.1:%s" % config['port'],
debug=False,
assets=config['docroot'])
factory.protocol = FerryServerProtocol
factory.setProtocolOptions(allowHixie76=True)
websocket = create_ferry_resource(spec_manager, factory)
root.putChild("ws", websocket)
root.putChild('proxy', ProxyResource())
auth_manager = AuthManager(settings)
return auth_manager.protectResource(root)
def get_project_settings(module=None, custom_settings=None):
crawler_settings = Settings()
if module is None:
module = settings.PROJECT_SETTINGS
crawler_settings.setmodule(module, priority='project')
if custom_settings:
assert isinstance(custom_settings, dict)
crawler_settings.setdict(custom_settings, priority='cmdline')
return crawler_settings
def import_from_old(request):
from scrapy.settings import Settings
from scrapy.crawler import CrawlerProcess
from yurasic_spider import SongSpider
settings = Settings()
settings.setmodule('yurasic_spider.settings', priority='project')
crawler = CrawlerProcess(settings)
crawler.crawl(SongSpider)
crawler.start()
def test_scrapy_spider():
settings = Settings()
settings.setmodule("tests.scrapy_spider.settings")
crawler = Crawler(MySpider, settings=settings)
crawler.signals.connect(reactor.stop, signal=signals.spider_closed)
crawler.crawl()
reactor.run()
stats = crawler.stats.spider_stats["example"]
assert stats["frontera/crawled_pages_count"] == 5
assert crawler.spider.callback_calls > 0
def __init__(self, spider):
Process.__init__(self)
setting = Settings()
setting.setmodule(settings,1)
self.crawler = Crawler(setting)
if not hasattr(project, 'crawler'):
self.crawler.configure()
self.crawler.signals.connect(reactor.stop, signal = signals.spider_closed)
self.spider = spider
def test_update_settings(self):
spider_settings = {'TEST1': 'spider', 'TEST2': 'spider'}
project_settings = {'TEST1': 'project', 'TEST3': 'project'}
self.spider_class.custom_settings = spider_settings
settings = Settings(project_settings, priority='project')
self.spider_class.update_settings(settings)
self.assertEqual(settings.get('TEST1'), 'spider')
self.assertEqual(settings.get('TEST2'), 'spider')
self.assertEqual(settings.get('TEST3'), 'project')
def _construct_scraper_settings():
"""Construct settings for scraper.
Method constructs settings from default scrapy settings and augments them
from loaded `CONFIGS`.
"""
if "scraper" in CONFIGS.keys():
global SCRAPER_SETTINGS
SCRAPER_SETTINGS = Settings()
SCRAPER_SETTINGS.setdict(CONFIGS["scraper"])
def __init__(self):
settings = Settings()
settings.setdict({
'USER_AGENT': 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)',
'FEED_FORMAT': 'json',
'DOWNLOAD_DELAY': 2,
'REACTOR_THREADPOOL_MAXSIZE': 2,
'LOG_LEVEL': 'WARNING'
}, priority='project')
self.process = CrawlerProcess(settings=settings)
def create_spider():
custom_settings = Settings()
custom_settings.setmodule(settings)
crawler = Crawler(
spidercls=desy_spider.DesySpider,
settings=custom_settings,
)
return desy_spider.DesySpider.from_crawler(
crawler,
source_folder='idontexist_but_it_does_not_matter',
)
def start(self):
settings = Settings()
# crawl responsibly
settings.set("USER_AGENT", "test")
crawler_obj = Spider()
crawler = Crawler(crawler_obj, settings)
# stop reactor when spider closes
crawler.signals.connect(self.stop, signal=signals.spider_closed)
crawler.crawl()
def __init__(self, download_func=None, settings=None):
self.download_func = download_func
if isinstance(settings, dict) or settings is None:
settings = Settings(settings)
resolve = functools.partial(self._key_for_pipe,
base_class_name="MediaPipeline",
settings=settings)
self.allow_redirects = settings.getbool(
resolve('MEDIA_ALLOW_REDIRECTS'), False
)
self._handle_statuses(self.allow_redirects)
def get_summaries_collection():
import pymongo
from scraper.guardianukscraper import settings
from scrapy.settings import Settings
sets = Settings()
sets.setmodule(settings, priority='project')
connection = pymongo.MongoClient(
sets['MONGODB_SERVER'],
sets['MONGODB_PORT']
)
db = connection[sets['MONGODB_DB']]
return db[sets['MONGODB_COLLECTION']]
def setUp(self):
s3reqh = S3DownloadHandler(Settings(), self.AWS_ACCESS_KEY_ID, \
self.AWS_SECRET_ACCESS_KEY, \
httpdownloadhandler=HttpDownloadHandlerMock)
self.download_request = s3reqh.download_request
self.spider = Spider('foo')
from datetime import datetime
from os.path import dirname, join
import pytest
from city_scrapers_core.constants import COMMISSION, PASSED
from city_scrapers_core.utils import file_response
from freezegun import freeze_time
from scrapy.settings import Settings
from city_scrapers.spiders.chi_board_elections import ChiBoardElectionsSpider
test_response = file_response(
join(dirname(__file__), "files", "chi_board_elections.html"),
url='https://app.chicagoelections.com/pages/en/board-meetings.aspx')
spider = ChiBoardElectionsSpider()
spider.settings = Settings(values={"CITY_SCRAPERS_ARCHIVE": False})
freezer = freeze_time('2018-11-30')
freezer.start()
parsed_items = [item for item in spider._next_meeting(test_response)]
freezer.stop()
def test_title():
assert parsed_items[0]['title'] == 'Electoral Board'
def test_description():
assert parsed_items[0]['description'] == ''
class FerryServerProtocol(WebSocketServerProtocol):
_handlers = {
'load': 'load_page',
'interact': 'interact_page'
}
assets = './'
settings = Settings()
@property
def tab(self):
return self.factory[self].tab
@property
def spider(self):
return self.factory[self].spider
@property
def spiderspec(self):
return self.factory[self].spiderspec
@property
def user(self):
return self.factory[self]
def onConnect(self, request):
try:
auth_info = json.loads(request.headers['x-auth-info'])
except (KeyError, TypeError):
return
self.session_id = ''
self.auth_info = auth_info
self.factory[self] = User(auth_info)
def onOpen(self):
if self not in self.factory:
self.sendClose(1000, 'Invalid Connection missing required '
'parameters')
def onMessage(self, payload, isbinary):
close_old_connections()
payload = payload.decode('utf-8')
data = json.loads(payload)
project = data.get('project', data.get('_meta', {}).get('project'))
storage = create_project_storage(project, author=self.user)
projects = storage.__class__.get_projects(self.user)
if project and str(project) not in projects:
self.sendMessage({'status': 4004, 'message': 'Project not found'})
return
deferred = defer.maybeDeferred(
wrap_callback, None, self._on_message, storage=storage, data=data)
deferred.addCallbacks(self.sendMessage,
partial(self.send_error, data))
def _on_message(self, storage, data):
if '_meta' in data and 'session_id' in data['_meta']:
self.session_id = data['_meta']['session_id']
if is_blacklisted(data.get('url', '')):
blacklist_error(data, self)
return
command = data['_command']
command = self._handlers.get(command, command)
with data_store_context():
commands = Commands(data, self, storage)
result = getattr(commands, command, lambda: None)()
if result:
result.setdefault('_command', data.get('_callback', command))
if '_meta' in data and 'id' in data['_meta']:
result['id'] = data['_meta']['id']
return result
def onClose(self, was_clean, code, reason):
if self in self.factory:
if self.tab is not None:
self.tab.close()
self.tab.network_manager.closed = True
msg_data = {'session': self.session_id,
'session_time': 0,
'user': self.user.name}
msg = (u'Websocket Closed: id=%(session)s t=%(session_time)s '
u'user=%(user)s command=' % (msg_data))
log.err(msg)
def sendMessage(self, payload, is_binary=False):
if isinstance(payload, dict) and '_command' in payload:
super(FerryServerProtocol, self).sendMessage(
json.dumps(payload, cls=ScrapyJSONEncoder, sort_keys=True),
is_binary
)
def send_error(self, data, failure):
e = failure.value
command = data.get('_callback', data.get('_command'))
id_ = data.get('_meta', {}).get('id')
if isinstance(e, BaseHTTPError):
code, reason, message = e.status, e.title, e.body
elif isinstance(e, KeyError):
requested_command = data.get('_command')
code = 4000
reason = "Unknown command"
if requested_command:
message = 'No command named "%s" found.' % requested_command
else:
message = "No command received"
else:
code = 500
reason = "Internal Server Error"
message = "An unexpected error has occurred."
log.err(failure)
event_id = getattr(failure, 'sentry_event_id', None)
if event_id:
message = "%s (Event ID: %s)" % (message, event_id)
response = {
'error': code,
'reason': reason,
'message': message,
}
if command:
response['_command'] = command
if id_:
response['id'] = id_
self.sendMessage(response)
def getElementByNodeId(self, nodeid):
self.tab.web_page.mainFrame().evaluateJavaScript(
'livePortiaPage.pyGetByNodeId(%s)' % nodeid
)
return self.js_api.getReturnedElement()
def open_tab(self, meta=None):
if meta is None:
meta = {}
manager = SplashQNetworkAccessManager(
request_middlewares=[],
response_middlewares=[],
verbosity=defaults.VERBOSITY
)
manager.setCache(None)
data = {}
data['uid'] = id(data)
self.factory[self].tab = PortiaBrowserTab(
network_manager=manager,
splash_proxy_factory=None,
verbosity=defaults.VERBOSITY,
render_options=RenderOptions(data, defaults.MAX_TIMEOUT),
visible=True,
)
manager.tab = self.tab
self.tab.register_callback('on_request', self._configure_requests)
self.tab.register_callback('on_response', self._set_tab_html)
main_frame = self.tab.web_page.mainFrame()
cookiejar = PortiaCookieJar(self.tab.web_page, self)
manager.cookiejar = cookiejar
manager.setCookieJar(cookiejar)
if meta.get('cookies'):
cookiejar.put_client_cookies(meta['cookies'])
main_frame.loadStarted.connect(self._on_load_started)
main_frame.loadFinished.connect(self._on_load_finished)
self.js_api = PortiaJSApi(self)
main_frame.javaScriptWindowObjectCleared.connect(
self._on_javascript_window_cleared)
main_frame.initialLayoutCompleted.connect(self._on_layout_completed)
self.tab.set_images_enabled(True)
self.tab.set_viewport(meta.get('viewport') or _DEFAULT_VIEWPORT)
self.tab.set_user_agent(meta.get('user_agent') or _DEFAULT_USER_AGENT)
self.tab.loaded = False
def _on_load_started(self):
self.load_id = short_guid()
self.sendMessage({'_command': 'loadStarted', 'id': self.load_id,
'url': self.tab.url})
self.tab.initial_layout_completed = False
def _on_load_finished(self):
if getattr(self.tab, '_raw_url', None) != self.tab.url:
page = self.tab.web_page
page.triggerAction(page.ReloadAndBypassCache, False)
self.sendMessage({'_command': 'loadFinished', 'url': self.tab.url,
'id': getattr(self, 'load_id', None)})
def _configure_requests(self, request, operation, data):
if request.hasRawHeader('Accept'):
url = six.binary_type(request.url().toEncoded())
url_path = urlparse(url).path.lower()
accepts = str(request.rawHeader('Accept')).lower()
if (accepts.startswith(STORED_TYPES) or _is_xml(accepts) or
url_path.endswith(STORED_EXTENSIONS)):
request.track_response_body = True
elif (accepts.startswith(IGNORED_TYPES) or
url_path.endswith(MEDIA_EXTENSIONS)):
drop_request(request)
def _set_tab_html(self, reply, har, content):
url = decode(reply.url().toString())
if content is not None and url == self.tab.url:
self.tab._raw_html = decode(content)
self.tab._raw_url = url
def _on_layout_completed(self):
if not getattr(self.tab, 'initial_layout_completed', False):
self.populate_window_object()
self.tab.initial_layout_completed = True
def _on_javascript_window_cleared(self):
if getattr(self.tab, 'initial_layout_completed', False):
self.populate_window_object()
def populate_window_object(self):
main_frame = self.tab.web_page.mainFrame()
main_frame.addToJavaScriptWindowObject('__portiaApi', self.js_api)
self.tab.run_js_files(
os.path.join(self.assets, 'splash_content_scripts'),
handle_errors=False)
def open_spider(self, meta, storage=None, project=None):
if not (meta.get('project') and meta.get('spider')):
return {'error': 4005, 'reason': 'No project specified'}
if (self.user.authorized_projects is not None and
meta['project'] not in self.user.authorized_projects and
not self.user.staff):
return {'error': 4004,
'reason': 'Project "%s" not found' % meta['project']}
spider_name = meta['spider']
if project is None:
project = Project(storage, id=meta.get('project'))
try:
spider_model = project.spiders[spider_name]
except (IOError, KeyError):
return {'error': 4004,
'reason': 'Spider "%s" not found' % spider_name}
spider_name, spider, items, extractors = load_spider_data(spider_model)
if not self.settings.get('SPLASH_URL'):
self.settings.set('SPLASH_URL', 'portia')
self.factory[self].spider = IblSpider(spider_name, spider, items,
extractors, self.settings)
self.factory[self].spiderspec = SpiderSpec(
project, spider_name, spider, items, extractors)
def __repr__(self):
return '{}({})'.format(self.__class__.__name__, str(self))
def __str__(self):
tab, spider, spec = '', '', ''
if self.tab:
try:
tab = '{}({})'.format(
self.tab.__class__.__name__, self.tab.url)
except RuntimeError:
tab = 'MISSING'
if self.spider:
spider = '{}({})'.format(
self.spider.__class__.__name__, self.spider.name)
if self.spiderspec:
spec = str(self.spiderspec)
return ', '.join(filter(bool, (tab, spider, spec)))
from scrapy.crawler import CrawlerProcess
from scrapy.settings import Settings
from les4.les.gb_parse.spiders.autoyoula import AutoyoulaSpider
if __name__ == '__main__':
crawler_settings = Settings()
crawler_settings.setmodule('gb_parse.settings')
crawler_process = CrawlerProcess(settings=crawler_settings)
crawler_process.crawl(AutoyoulaSpider)
crawler_process.start()
def setUp(self):
self.crawler = Crawler(DefaultSpider, Settings())
class FerryServerProtocol(WebSocketServerProtocol):
_handlers = {
'load': load_page,
'interact': interact_page,
'close_tab': close_tab,
'heartbeat': lambda d, s: None,
'resize': resize,
'resolve': resolve,
'extract_items': extract_items,
'save_html': save_html,
'update_spider': update_spider
}
assets = './'
settings = Settings()
@property
def tab(self):
return self.factory[self].tab
@property
def spider(self):
return self.factory[self].spider
@property
def spiderspec(self):
return self.factory[self].spiderspec
@property
def user(self):
return self.factory[self]
def onConnect(self, request):
try:
auth_info = json.loads(request.headers['x-auth-info'])
except (KeyError, TypeError):
return
self.session_id = ''
self.auth_info = auth_info
self.factory[self] = User(auth_info)
def onOpen(self):
if self not in self.factory:
self.sendClose(1000, 'Invalid Connection missing required '
'parameters')
def onMessage(self, payload, isbinary):
close_old_connections()
pool = getattr(Repoman, 'pool', None)
payload = payload.decode('utf-8')
data = json.loads(payload)
project = data.get('project', data.get('_meta', {}).get('project'))
self.storage = create_project_storage(project, author=self.user)
projects = self.storage.__class__.get_projects(self.user)
if project and str(project) not in projects:
self.sendMessage({'status': 4004, 'message': 'Project not found'})
return
if pool is not None:
deferred = defer.maybeDeferred(
pool.run_deferred_with_connection, wrap_callback,
self._on_message, self.storage, data=data)
else:
deferred = defer.maybeDeferred(
wrap_callback, None, self._on_message, self.storage, data=data)
deferred.addCallbacks(self.sendMessage,
partial(self.send_error, data))
def _on_message(self, data):
if '_meta' in data and 'session_id' in data['_meta']:
self.session_id = data['_meta']['session_id']
if is_blacklisted(data.get('url', ''), self.settings):
blacklist_error(data, self)
return
command = data['_command']
with data_store_context():
result = self._handlers[command](data, self)
if result:
result.setdefault('_command', data.get('_callback', command))
if '_meta' in data and 'id' in data['_meta']:
result['id'] = data['_meta']['id']
return result
def onClose(self, was_clean, code, reason):
if self in self.factory:
if self.tab is not None:
self.tab.close()
self.tab.network_manager.closed = True
msg_data = {'session': self.session_id,
'session_time': 0,
'user': self.user.name}
msg = (u'Websocket Closed: id=%(session)s t=%(session_time)s '
u'user=%(user)s command=' % (msg_data))
log.err(msg)
def sendMessage(self, payload, is_binary=False):
if isinstance(payload, dict) and '_command' in payload:
super(FerryServerProtocol, self).sendMessage(
json.dumps(payload, cls=ScrapyJSONEncoder, sort_keys=True),
is_binary
)
self.factory[self].spider, self.storage = None, None
def send_error(self, data, failure):
e = failure.value
command = data.get('_callback', data.get('_command'))
id_ = data.get('_meta', {}).get('id')
if isinstance(e, BaseHTTPError):
code, reason, message = e.status, e.title, e.body
elif isinstance(e, KeyError):
requested_command = data.get('_command')
code = 4000
reason = "Unknown command"
if requested_command:
message = 'No command named "%s" found.' % requested_command
else:
message = "No command received"
else:
code = 500
reason = "Internal Server Error"
message = "An unexpected error has occurred."
log.err(failure)
event_id = getattr(failure, 'sentry_event_id', None)
if event_id:
message = "%s (Event ID: %s)" % (message, event_id)
response = {
'error': code,
'reason': reason,
'message': message,
}
if command:
response['_command'] = command
if id_:
response['id'] = id_
self.sendMessage(response)
def getElementByNodeId(self, nodeid):
self.tab.web_page.mainFrame().evaluateJavaScript(
'livePortiaPage.pyGetByNodeId(%s)' % nodeid
)
return self.js_api.getReturnedElement()
def open_tab(self, meta=None):
if meta is None:
meta = {}
manager = PortiaNetworkManager(
request_middlewares=[],
response_middlewares=[],
verbosity=defaults.VERBOSITY
)
manager.setCache(None)
data = {}
data['uid'] = id(data)
self.factory[self].tab = BrowserTab(
network_manager=manager,
splash_proxy_factory=None,
verbosity=0,
render_options=RenderOptions(data, defaults.MAX_TIMEOUT),
visible=True,
)
manager.tab = self.tab
main_frame = self.tab.web_page.mainFrame()
cookiejar = PortiaCookieJar(self.tab.web_page, self)
manager.cookiejar = cookiejar
manager.setCookieJar(cookiejar)
if meta.get('cookies'):
cookiejar.put_client_cookies(meta['cookies'])
main_frame.loadStarted.connect(self._on_load_started)
self.js_api = PortiaJSApi(self)
main_frame.javaScriptWindowObjectCleared.connect(
self.populate_window_object
)
self.tab.set_images_enabled(True)
self.tab.set_viewport(meta.get('viewport') or _DEFAULT_VIEWPORT)
self.tab.set_user_agent(meta.get('user_agent') or _DEFAULT_USER_AGENT)
self.tab.loaded = False
def _on_load_started(self):
self.sendMessage({'_command': 'loadStarted'})
def populate_window_object(self):
main_frame = self.tab.web_page.mainFrame()
main_frame.addToJavaScriptWindowObject('__portiaApi', self.js_api)
self.tab.run_js_files(
os.path.join(self.assets, 'splash_content_scripts'),
handle_errors=False)
def open_spider(self, meta, project=None):
if not (meta.get('project') and meta.get('spider')):
return {'error': 4005, 'reason': 'No project specified'}
if (self.user.authorized_projects is not None and
meta['project'] not in self.user.authorized_projects and
not self.user.staff):
return {'error': 4004,
'reason': 'Project "%s" not found' % meta['project']}
spider_name = meta['spider']
# project_meta = meta.get('project')
# project_id = (project_meta if isinstance(project_meta, six.string_types)
# else project_meta.id)
# project = Project(self.storage, id=project_id)
if project is None:
project = Project(self.storage, id=meta.get('project'))
try:
spider_model = project.spiders[spider_name]
except IOError:
return {'error': 4003,
'reason': 'Spider "%s" not found' % spider_name}
spider_name, spider, items, extractors = load_spider_data(spider_model)
if not self.settings.get('SPLASH_URL'):
self.settings.set('SPLASH_URL', 'portia')
self.factory[self].spider = IblSpider(spider_name, spider, items,
extractors, self.settings)
self.factory[self].spiderspec = SpiderSpec(
project, spider_name, spider, items, extractors)
def update_spider(self, meta, spider=None, template=None, items=None,
extractors=None):
if not hasattr(self.factory[self], 'spiderspec'):
return self.open_spider(meta)
spec = self.factory[self].spiderspec
if spec is None or spec.name != meta.get('spider'):
return self.open_spider(meta)
items = items or spec.items
extractors = extractors or spec.extractors
if spider:
spider['templates'] = spec.spider['templates']
else:
spider = spec.spider
if template:
for idx, tmpl in enumerate(spider['templates']):
if template['original_body'] == tmpl['original_body']:
spider['templates'][idx] = template
break
else:
spider['templates'].append(template)
self.factory[self].spider = IblSpider(meta['spider'], spider, items,
extractors, self.settings)
self.factory[self].spiderspec = SpiderSpec(
spec.project, meta['spider'], spider, items, extractors)
def setUp(self):
self.spider = Mock()
self.settings = Settings()
def test_feed_export_config_implicit_formats(self):
settings = Settings()
self.assertEqual(
{'items_1.json': {'format': 'json'}, 'items_2.xml': {'format': 'xml'}, 'items_3.csv': {'format': 'csv'}},
feed_process_params_from_cli(settings, ['items_1.json', 'items_2.xml', 'items_3.csv'])
)
def test_feed_export_config_mismatch(self):
settings = Settings()
self.assertRaises(
UsageError,
feed_process_params_from_cli, settings, ['items1.dat', 'items2.dat'], 'noformat'
)
def test_feed_export_config_stdout(self):
settings = Settings()
self.assertEqual(
{'stdout:': {'format': 'pickle'}},
feed_process_params_from_cli(settings, ['-:pickle'])
)
def test_feed_export_config_overwrite(self):
settings = Settings()
self.assertEqual(
{'output.json': {'format': 'json', 'overwrite': True}},
feed_process_params_from_cli(settings, [], None, ['output.json'])
)
def setUp(self):
self.crawler = mock.MagicMock()
self.crawler.settings = Settings()
self.crawler.engine.download = mock.MagicMock()
from scrapy.crawler import CrawlerProcess
from scrapy.settings import Settings
from edu_parse.spiders.autoyoula import AutoyoulaSpider
if __name__ == '__main__':
crawler_settings = Settings()
crawler_settings.setmodule("edu_parse.settings")
crawler_proc= CrawlerProcess(settings=crawler_settings)
crawler_proc.crawl(AutoyoulaSpider)
crawler_proc.start()
pass
def setUp(self):
self.tmpname = self.mktemp()
with open(self.tmpname + '^', 'w') as f:
f.write('0123456789')
self.download_request = FileDownloadHandler(
Settings()).download_request
def start_crawler(spider, search):
# Set up spider
spider = TripAdvisorSpider(search=search)
# Set up settings
settings = Settings()
# settings.overrides['FEED_FORMAT']='csv'
# settings.overrides['FEED_URI']='tripadvisor_{0}.csv'.format(search)
settings.set('CLOSESPIDER_ITEMCOUNT', False)
settings.set('ROBOTSTXT_OBEY', False)
settings.set('COOKIES_ENABLED', False)
settings.set(
'ITEM_PIPELINES',
{'tripadvisor_scraper.pipelines.TripadvisorScraperPipeline': 300})
settings.set('DOWNLOAD_DELAY', 3)
settings.set('LOG_FILENAME', 'log.log')
# settings.overrides['LOG_FILENAME'] = 'log.log'
# settings.overrides['ROBOTSTXT_OBEY'] = False # Ignore robots.txt
# settings.overrides['CLOSESPIDER_ITEMCOUNT']=1
# settings.overrides['DOWNLOAD_DELAY'] = 3
# settings.overrides['COOKIES_ENABLED'] = False
# settings.overrides['ITEM_PIPELINES'] = {
# 'tripadvisor_scraper.pipelines.TripadvisorScraperPipeline': 300,
# }
# Set up crawler
crawler = Crawler(spider, settings)
# crawler.configure()
crawler.signals.connect(spider_closed, signal=signals.spider_closed)
crawler.crawl(spider)
class StorageTest(TestCase):
def setUp(self):
self.spider = Spider('foo')
self.settings = Settings()
self.settings.setmodule(default_settings)
def tearDown(self):
pass
def test_environment(self):
oldenv = os.environ.copy()
os.environ['http_proxy'] = http_proxy = 'https://proxy.for.http:3128'
os.environ['https_proxy'] = https_proxy = 'http://proxy.for.https:8080'
os.environ.pop('file_proxy', None)
settings = deepcopy(self.settings)
storage = EnvironmentStorage(settings)
storage.open_spider(self.spider)
self.assertTrue(storage, True)
self.assertIn('http', storage)
self.assertIn('https', storage)
self.assertNotIn('file_proxy', storage)
self.assertSequenceEqual(
storage['http'],
get_proxy(http_proxy, 'http', storage.auth_encoding))
self.assertSequenceEqual(
storage['https'],
get_proxy(https_proxy, 'https', storage.auth_encoding))
storage.close_spider(self.spider)
os.environ = oldenv
def test_settings(self):
http_proxy_1 = 'https://proxy.for.http.1:3128'
http_proxy_2 = 'https://proxy.for.http.2:3128'
https_proxy_1 = 'http://proxy.for.https.1:8080'
https_proxy_2 = 'http://proxy.for.https.2:8080'
local_settings = {
'HTTPPROXY_ENABLED': True,
'HTTPPROXY_PROXIES': {
'http': [http_proxy_1, http_proxy_2],
'https': [https_proxy_1, https_proxy_2]
}
}
settings = deepcopy(self.settings)
settings.setdict(local_settings)
storage = SettingsStorage(settings)
storage.open_spider(self.spider)
self.assertTrue(storage, True)
self.assertIn('http', storage)
self.assertIn('https', storage)
self.assertSequenceEqual(
storage['http'],
get_proxy(http_proxy_1, 'http', storage.auth_encoding))
storage.close_spider(self.spider)
def main():
global settings
from scrapy import cmdline
from scrapy.settings import Settings
parser = argparse.ArgumentParser(description=__doc__, add_help=False)
parser.add_argument('-h',
'--help',
dest='help',
help='获取帮助信息',
action='store_true',
default=False)
act_group = parser.add_argument_group(title='操作选项组')
act_group.add_argument('-r',
'--run',
dest='cmd',
help='运行爬虫获取数据',
action='store_const',
const='runspider')
act_group.add_argument('-s',
'--shell',
dest='cmd',
help='控制台调试',
action='store_const',
const='shell')
act_group.add_argument('-v',
'--view',
dest='cmd',
help='使用浏览器打开蜘蛛获取的URL页面',
action='store_const',
const='view')
run_group = parser.add_argument_group(title='运行操作组')
run_group.add_argument('-n',
'--limit-num',
dest='limit',
default=0,
help='限制总请求次数，默认为0不限制',
type=int)
run_group.add_argument('-m',
'--max-request-num',
dest='max',
default=30,
help='同时最大请求数，默认为30，0则不限制',
type=int)
run_group.add_argument("-a",
dest="spargs",
action="append",
default=[],
metavar="NAME=VALUE",
help="设置爬虫参数（可以重复）")
run_group.add_argument("-o",
"--output",
metavar="FILE",
help="输出 items 结果集 值FILE (使用 -o 将定向至 stdout)")
run_group.add_argument("-t",
"--output-format",
metavar="FORMAT",
help="基于 -o 选项，使用指定格式输出 items")
run_group.add_argument('-d',
'--dist',
help='分布式运行，用于其他进程提交数据',
action='store_true',
default=False)
gen_group = parser.add_argument_group(title='通用选择项')
gen_group.add_argument('-u',
'--url',
help='设置URL，运行操作设置该项则为起始爬取URL，\
调试操作设置则为调试URL，查看操作则为打开查看URL'
)
args = parser.parse_args()
if args.help:
parser.print_help()
elif args.cmd:
settings = Settings(settings)
if args.cmd == 'runspider':
argv = [sys.argv[0], args.cmd, sys.argv[0]]
for vo in run_group._group_actions:
opt = vo.option_strings[0]
val = args.__dict__.get(vo.dest)
if val == vo.default:
continue
if isinstance(val, (list, tuple)):
val = ' '.join(val)
if vo.dest == 'limit':
settings['CLOSESPIDER_ITEMCOUNT'] = val
continue
elif vo.dest == 'max':
settings['CONCURRENT_REQUESTS'] = val
continue
elif vo.dest == 'dest':
settings['DESTRIBUT_RUN'] = val
continue
argv.extend([opt, val])
if args.url:
argv.extend(['-a', 'START_URL=%s' % args.url])
elif args.cmd == 'shell':
argv = [sys.argv[0], args.cmd]
if args.url:
argv.append(args.url)
elif args.cmd == 'view':
if not args.url:
print('please setting --url option')
return None
argv = [sys.argv[0], args.cmd, args.url]
cmdline.execute(argv, settings)
else:
parser.print_usage()
def test_feed_export_config_invalid_format(self):
settings = Settings()
self.assertRaises(UsageError, feed_process_params_from_cli, settings, ['items.dat'], 'noformat')
def setUp(self):
self.download_handler = DataURIDownloadHandler(Settings())
self.download_request = self.download_handler.download_request
self.spider = Spider('foo')
from scrapy.crawler import CrawlerProcess
from scrapy.settings import Settings
from avito_parse import settings
from avito_parse.spiders.avito import AvitoSpider
if __name__ == '__main__':
scr_settings = Settings()
scr_settings.setmodule(settings)
process = CrawlerProcess(settings=scr_settings)
process.crawl(AvitoSpider)
process.start()
# import dmoz spider class
from DmozSpider import DmozSpider
# scrapy api
from scrapy import signals, log
from twisted.internet import reactor
from scrapy.crawler import Crawler
from scrapy.settings import Settings
def spider_closing(spider):
"""Activates on spider closed signal"""
log.msg("Closing reactor", level=log.INFO)
reactor.stop()
#log.(loglevel=log.DEBUG)
settings = Settings()
# crawl responsibly
settings.set("USER_AGENT", "Kiran Koduru (+http://kirankoduru.github.io)")
crawler = Crawler(DmozSpider(),settings)
# stop reactor when spider closes
crawler.signals.connect(spider_closing, signal=signals.spider_closed)
#crawler.configure()
crawler.crawl()
#crawler.start()
reactor.run()
def setUp(self):
self.tempdir = mkdtemp()
self.pipeline = FilesPipeline.from_settings(
Settings({'FILES_STORE': self.tempdir}))
self.pipeline.download_func = _mocked_download_func
self.pipeline.open_spider(None)
def setUp(self):
crawler = get_crawler(Spider)
self.spider = Spider.from_crawler(crawler, name='foo')
self.mw = HttpErrorMiddleware(Settings({}))
self.req = Request('http://scrapytest.org')
self.res200, self.res404 = _responses(self.req, [200, 404])
def test_enabled_from_settings(self):
settings = Settings()
mwman = TestMiddlewareManager.from_settings(settings)
classes = [x.__class__ for x in mwman.middlewares]
self.assertEqual(classes, [M1, M3])
"//*[contains(@itemprop, 'track')]//@href").extract()
for link in link_to_lyrics:
yield Request(url=''.join(('http://www.songteksten.nl', link)),
callback=self.parse_lyrics)
def parse_lyrics(self, response):
hxs = Selector(response)
item = LyricsSearchItem()
item['lyrics'] = hxs.xpath(
"//*[contains(@itemprop, 'description')]/text()").extract()
return item
def callback(spider, reason):
stats = spider.crawler.stats.get_stats()
reactor.stop()
settings = Settings()
settings.set('ITEM_PIPELINES', {'pipeline.LyricsSearchPipeline': 100})
def crawl():
crawler = Crawler(settings)
spider = MySpider()
crawler.signals.connect(callback, signal=signals.spider_closed)
crawler.configure()
crawler.crawl(spider)
crawler.start()
reactor.run()
def setUp(self):
self.tmpname = self.mktemp()
fd = open(self.tmpname + '^', 'w')
fd.write('0123456789')
fd.close()
self.download_request = FileDownloadHandler(Settings()).download_request
SUBMIT_TYPES = {'submit button'}
DEFAULT_POST_HEADERS = {b'Content-Type': b'application/x-www-form-urlencoded'}
USER_AGENT = ('Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 '
'(KHTML, like Gecko) Ubuntu Chromium/43.0.2357.130 '
'Chrome/43.0.2357.130 Safari/537.36')
base_settings = Settings(values=dict(
TELNETCONSOLE_ENABLED=False,
ROBOTSTXT_OBEY=False,
DOWNLOAD_DELAY=2.0,
DEPTH_PRIORITY=1,
CONCURRENT_REQUESTS=2,
CONCURRENT_REQUESTS_PER_DOMAIN=2,
SCHEDULER_DISK_QUEUE='scrapy.squeues.PickleFifoDiskQueue',
SCHEDULER_MEMORY_QUEUE='scrapy.squeues.FifoMemoryQueue',
# DOWNLOADER_MIDDLEWARES are set in get_settings
USER_AGENT=USER_AGENT,
DOWNLOADER_MIDDLEWARES={
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': None,
# Placed before splash middleware
'autologin.middleware.ProxyMiddleware': 720,
},
))
def crawl_runner(extra_settings=None):
settings = base_settings.copy()
if extra_settings is not None:
settings.update(extra_settings, priority='cmdline')
if settings.get('SPLASH_URL'):
from scrapy.crawler import CrawlerProcess
from scrapy.settings import Settings
from bookparser import settings
from bookparser.spiders.book24 import Book24Spider
from bookparser.spiders.labirint import LabirintSpider
if __name__ == "__main__":
crawler_settings = Settings()
crawler_settings.setmodule(settings)
process = CrawlerProcess(settings=crawler_settings)
process.crawl(Book24Spider)
process.crawl(LabirintSpider)
process.start()
def setUp(self):
self.spider = Spider('foo')
self.settings = Settings()
self.settings.setmodule(default_settings)
def setUp(self):
self.spider = Spider('foo')
self.mw = HttpErrorMiddleware(Settings({'HTTPERROR_ALLOW_ALL': True}))
self.req = Request('http://scrapytest.org')
self.res200, self.res404, self.res402 = _responses(
self.req, [200, 404, 402])
