def process_response(self, request, response, spider):
stats.inc_value("crawled_url_num", spider=spider)
stats.inc_value("crawled_page_size", count=len(response.body), spider=spider)
# log.msg('download page:%s, size:%s, content-length:%s'\
# %(response.url, len(response.body),
# response.headers.get('Content-Length')))
return response
def handle_spider_error(self, _failure, request, spider, propagated_failure=None):
referer = request.headers.get('Referer', None)
msg = "Spider error processing <%s> (referer: <%s>)" % \
(request.url, referer)
log.err(_failure, msg, spider=spider)
stats.inc_value("spider_exceptions/%s" % _failure.value.__class__.__name__, \
spider=spider)
def process_request(self, request, spider):
stats.inc_value('downloader/request_count')
stats.inc_value('downloader/request_count', spider=spider)
stats.inc_value('downloader/request_method_count/%s' % request.method, spider=spider)
reqlen = len(request_httprepr(request))
stats.inc_value('downloader/request_bytes', reqlen, spider=spider)
stats.inc_value('downloader/request_bytes', reqlen)
def process_response(self, request, response, spider):
if (self.is_cacheable(request)
and self.is_cacheable_response(response)
and 'cached' not in response.flags):
self.storage.store_response(spider, request, response)
stats.inc_value('httpcache/store', spider=spider)
return response
def stats_spider_closing(self, spider, reason):
stats.set_value('finish_time',
datetime.datetime.utcnow(),
spider=spider)
stats.set_value('finish_status',
'OK' if reason == 'finished' else reason,
spider=spider)
stats.inc_value('spider_count/%s' % reason, spider=spider)
def stats_spider_opened(self, spider):
stats.set_value('start_time',
datetime.datetime.utcnow(),
spider=spider)
stats.set_value('envinfo/host',
stats.get_value('envinfo/host'),
spider=spider)
stats.inc_value('spider_count/opened')
def process_response(self, request, response, spider):
stats.inc_value('downloader/response_count')
stats.inc_value('downloader/response_count', spider=spider)
stats.inc_value('downloader/response_status_count/%s' % response.status, spider=spider)
reslen = len(response_httprepr(response))
stats.inc_value('downloader/response_bytes', reslen, spider=spider)
stats.inc_value('downloader/response_bytes', reslen)
return response
def process_request(self, request, spider):
stats.inc_value('downloader/request_count')
stats.inc_value('downloader/request_count', spider=spider)
stats.inc_value('downloader/request_method_count/%s' % request.method,
spider=spider)
reqlen = len(request_httprepr(request))
stats.inc_value('downloader/request_bytes', reqlen, spider=spider)
stats.inc_value('downloader/request_bytes', reqlen)
def process_response(self, request, response, spider):
doc = request.meta['terms']
if self.index.appendif(doc, response.url, 0.0):
return response
stats.inc_value('downloader/near_duplicates')
raise IgnoreRequest
def handle_spider_error(self, _failure, request, response, spider):
exc = _failure.value
if isinstance(exc, CloseSpider):
self.crawler.engine.close_spider(spider, exc.reason or "cancelled")
return
log.err(_failure, "Spider error processing %s" % request, spider=spider)
send_catch_log(signal=signals.spider_error, failure=_failure, response=response, spider=spider)
stats.inc_value("spider_exceptions/%s" % _failure.value.__class__.__name__, spider=spider)
def process_response(self, request, response, spider):
stats.inc_value('crawled_url_num', spider=spider)
stats.inc_value('crawled_page_size',
count=len(response.body),
spider=spider)
#log.msg('download page:%s, size:%s, content-length:%s'\
# %(response.url, len(response.body),
# response.headers.get('Content-Length')))
return response
def handle_spider_error(self, _failure, request, response, spider):
exc = _failure.value
if isinstance(exc, CloseSpider):
self.crawler.engine.close_spider(spider, exc.reason or 'cancelled')
return
log.err(_failure, "Spider error processing %s" % request, spider=spider)
send_catch_log(signal=signals.spider_error, failure=_failure, response=response, \
spider=spider)
stats.inc_value("spider_exceptions/%s" % _failure.value.__class__.__name__, \
spider=spider)
def process_item(self, item, spider):
self.file.write('%s\n' % item['domain'])
domain = Domain.get(item['domain'])
if not domain:
stats.inc_value('found_new_domain')
log.msg("Found new domain: %s" % item['domain'])
Domain.objects.create(domain_name=item['domain'],
monitoring_status='new',
metadata_status='new')
def process_response(self, request, response, spider):
stats.inc_value('downloader/response_count')
stats.inc_value('downloader/response_count', spider=spider)
stats.inc_value('downloader/response_status_count/%s' %
response.status,
spider=spider)
reslen = len(response_httprepr(response))
stats.inc_value('downloader/response_bytes', reslen, spider=spider)
stats.inc_value('downloader/response_bytes', reslen)
return response
def parse(self, response):
self.log('Response:%s, type:%s' % (response.url, type(response)))
self.parser_manager.process_response(response, self)
stats.inc_value('crawled_url_num', spider=self)
stats.inc_value(
'crawled_page_size',
count=len(response.body),
spider=self,
)
def handle_spider_error(self,
_failure,
request,
spider,
propagated_failure=None):
referer = request.headers.get('Referer', None)
msg = "Spider error processing <%s> (referer: <%s>)" % \
(request.url, referer)
log.err(_failure, msg, spider=spider)
stats.inc_value("spider_exceptions/%s" % _failure.value.__class__.__name__, \
spider=spider)
def _dqpush(self, request):
if self.dqs is None:
return
try:
reqd = request_to_dict(request, self.spider)
self.dqs.push(reqd, request.priority)
except ValueError: # non serializable request
return
else:
stats.inc_value('scheduler/disk_enqueued', spider=self.spider)
return True
def process_request(self, request, spider):
if not self.is_cacheable(request):
return
response = self.storage.retrieve_response(spider, request)
if response and self.is_cacheable_response(response):
response.flags.append("cached")
stats.inc_value("httpcache/hit", spider=spider)
return response
stats.inc_value("httpcache/miss", spider=spider)
if self.ignore_missing:
raise IgnoreRequest("Ignored request not in cache: %s" % request)
def process_request(self, request, spider):
if not self.is_cacheable(request):
return
response = self.storage.retrieve_response(spider, request)
if response and self.is_cacheable_response(response):
response.flags.append('cached')
stats.inc_value('httpcache/hit', spider=spider)
return response
stats.inc_value('httpcache/miss', spider=spider)
if self.ignore_missing:
raise IgnoreRequest("Ignored request not in cache: %s" % request)
def _filter(request):
if isinstance(request, Request):
depth = response.request.meta['depth'] + 1
request.meta['depth'] = depth
if self.maxdepth and depth > self.maxdepth:
log.msg("Ignoring link (depth > %d): %s " % (self.maxdepth, request.url), \
level=log.DEBUG, spider=spider)
return False
elif self.stats:
stats.inc_value('request_depth_count/%s' % depth, spider=spider)
if depth > stats.get_value('request_depth_max', 0, spider=spider):
stats.set_value('request_depth_max', depth, spider=spider)
return True
def parse_item(self, response):
item = RecipebotItem()
doc = response.meta['terms']
# decide if the page is interesting
if not self.sim.is_relevant(doc):
stats.inc_value('recipe/filtered_out') # probably not recipe page
return
item['url'] = response.url
return item
def parse_item(self, response):
item = ScifibotItem()
# clean body
orig_body = response.body_as_unicode()
body = remove_tags_with_content(orig_body,
which_ones=('script', 'head'))
body = remove_tags(remove_comments(body))
tokens = tokenize(body.lower())
# decide if the page is interesting
if not is_relevant(tokens):
stats.inc_value('scifi/filtered_out') # probably not scifi page
return
item['keywords'] = tokens
item['page'] = orig_body
item['url'] = response.url
return item
def new_callback(*args, **kwargs):
tbefore = time()
mbefore = self._memusage()
r = function(*args, **kwargs)
mafter = self._memusage()
ct = time() - tbefore
tcc = stats.get_value('profiling/total_callback_time', 0, spider=spider)
sct = stats.get_value('profiling/slowest_callback_time', 0, spider=spider)
stats.set_value('profiling/total_callback_time', tcc+ct, spider=spider)
if ct > sct:
stats.set_value('profiling/slowest_callback_time', ct, spider=spider)
stats.set_value('profiling/slowest_callback_name', function.__name__, \
spider=spider)
stats.set_value('profiling/slowest_callback_url', args[0].url, \
spider=spider)
if self._memusage:
stats.inc_value('profiling/total_mem_allocated_in_callbacks', \
count=mafter-mbefore, spider=spider)
return r
def parse_item(self, response):
item = RecipebotItem()
body = response.meta['body']
result = self.detector.extract(body)
if len(result) == 0:
stats.inc_value('recipe/filtered_out') # probably not recipe page
return
item['url'] = response.url
item['ingredients'] = []
for item in result:
if item[2] >= 0.25:
item['ingredients'].append(item[0])
return item
def process_spider_output(self, response, result, spider):
def _filter(request):
if isinstance(request, Request):
depth = response.request.meta['depth'] + 1
request.meta['depth'] = depth
if self.maxdepth and depth > self.maxdepth:
log.msg("Ignoring link (depth > %d): %s " % (self.maxdepth, request.url), \
level=log.DEBUG, spider=spider)
return False
elif self.stats:
stats.inc_value('request_depth_count/%s' % depth, spider=spider)
if depth > stats.get_value('request_depth_max', 0, spider=spider):
stats.set_value('request_depth_max', depth, spider=spider)
return True
# base case (depth=0)
if self.stats and 'depth' not in response.request.meta:
response.request.meta['depth'] = 0
stats.inc_value('request_depth_count/0', spider=spider)
return (r for r in result or () if _filter(r))
def process_exception(self, request, exception, spider):
ex_class = "%s.%s" % (exception.__class__.__module__,
exception.__class__.__name__)
stats.inc_value('downloader/exception_count')
stats.inc_value('downloader/exception_count', spider=spider)
stats.inc_value('downloader/exception_type_count/%s' % ex_class,
spider=spider)
def item_dropped(self, item, spider, exception):
reason = exception.__class__.__name__
stats.inc_value('item_dropped_count', spider=spider)
stats.inc_value('item_dropped_reasons_count/%s' % reason,
spider=spider)
def _mqpush(self, request):
stats.inc_value('scheduler/memory_enqueued', spider=self.spider)
self.mqs.push(request, -request.priority)
def __len__(self):
return len(self.dqs) + len(self.mqs) if self.dqs else len(self.mqs)
def _dqpush(self, request):
if self.dqs is None:
return
try:
reqd = request_to_dict(request, self.spider)
self.dqs.push(reqd, -request.priority)
except ValueError, e: # non serializable request
if self.logunser:
log.msg("Unable to serialize request: %s - reason: %s" % \
(request, str(e)), level=log.ERROR, spider=self.spider)
return
else:
stats.inc_value('scheduler/disk_enqueued', spider=self.spider)
return True
def _mqpush(self, request):
stats.inc_value('scheduler/memory_enqueued', spider=self.spider)
self.mqs.push(request, -request.priority)
def _dqpop(self):
if self.dqs:
d = self.dqs.pop()
if d:
return request_from_dict(d, self.spider)
def _newmq(self, priority):
return self.mqclass()
def inc_stats(self, spider, status):
stats.inc_value('image_count', spider=spider)
stats.inc_value('image_status_count/%s' % status, spider=spider)
def item_dropped(self, item, spider, exception):
reason = exception.__class__.__name__
stats.inc_value("item_dropped_count", spider=spider)
stats.inc_value("item_dropped_reasons_count/%s" % reason, spider=spider)
stats.inc_value("item_dropped_count")
def item_scraped(self, item, spider):
stats.inc_value('item_scraped_count', spider=spider)
stats.inc_value('item_scraped_count')
def item_passed(self, item, spider):
stats.inc_value('item_passed_count', spider=spider)
stats.inc_value('item_passed_count')
def inc_stats(self, spider, status):
stats.inc_value("image_count", spider=spider)
stats.inc_value("image_status_count/%s" % status, spider=spider)
def item_scraped(self, item, spider):
stats.inc_value('item_scraped_count', spider=spider)
def parse(self, response):
self.log('Response:%s, type:%s' %(response.url, type(response)))
self.parser_manager.process_response(response, self)
stats.inc_value('crawled_url_num', spider=self)
stats.inc_value('crawled_page_size', count=len(response.body), spider=self,)
def process_response(self, request, response, spider):
if (self.is_cacheable(request) and self.is_cacheable_response(response)
and 'cached' not in response.flags):
self.storage.store_response(spider, request, response)
stats.inc_value('httpcache/store', spider=spider)
return response
def stats_spider_closing(self, spider, reason):
stats.set_value('finish_time', datetime.datetime.utcnow(), spider=spider)
stats.set_value('finish_status', 'OK' if reason == 'finished' else reason, spider=spider)
stats.inc_value('spider_count/%s' % reason, spider=spider)
def stats_spider_opened(self, spider):
stats.set_value('start_time', datetime.datetime.utcnow(), spider=spider)
stats.set_value('envinfo/host', stats.get_value('envinfo/host'), spider=spider)
stats.inc_value('spider_count/opened')
def process_response(self, request, response, spider):
if self.is_cacheable(request) and self.is_cacheable_response(response) and "cached" not in response.flags:
self.storage.store_response(spider, request, response)
stats.inc_value("httpcache/store", spider=spider)
return response
def stats_spider_opened(self, spider):
stats.set_value("start_time", datetime.datetime.utcnow(), spider=spider)
stats.set_value("envinfo/host", stats.get_value("envinfo/host"), spider=spider)
stats.inc_value("spider_count/opened")
def inc_stats(self, spider, status):
stats.inc_value('image_count', spider=spider)
stats.inc_value('image_status_count/%s' % status, spider=spider)
def stats_spider_closing(self, spider, reason):
stats.set_value("finish_time", datetime.datetime.utcnow(), spider=spider)
stats.set_value("finish_status", "OK" if reason == "finished" else reason, spider=spider)
stats.inc_value("spider_count/%s" % reason, spider=spider)
def process_exception(self, request, exception, spider):
ex_class = "%s.%s" % (exception.__class__.__module__, exception.__class__.__name__)
stats.inc_value('downloader/exception_count', spider=spider)
stats.inc_value('downloader/exception_type_count/%s' % ex_class, spider=spider)
def item_passed(self, item, spider):
stats.inc_value("item_passed_count", spider=spider)
stats.inc_value("item_passed_count")
