|
|
# Define here the models for your spider middleware
|
|
|
#
|
|
|
# See documentation in:
|
|
|
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
|
|
|
|
|
from scrapy import signals
|
|
|
|
|
|
# useful for handling different item types with a single interface
|
|
|
from itemadapter import is_item, ItemAdapter
|
|
|
|
|
|
# from copy import deepcopy
|
|
|
# import regex
|
|
|
|
|
|
# class SplitByStreet:
|
|
|
|
|
|
# @classmethod
|
|
|
|
|
|
# # Une fonction qui sépare les adresses en fonction des noms de rue
|
|
|
# def splitStreet(self, value):
|
|
|
# # Le regex qui évalue là où il faut séparer la chaîne de caractère
|
|
|
# # (présence de "et / - + ainsi que"
|
|
|
# # sans que ce séparateur ne soit placé près d'un groupe de numéros de la même rue)
|
|
|
# expr = r"((?<!(\d\sa)|(\d\sb)|(\d\sbis)|(\d\ster)|(\d)|(\da)|(\db)|(\dbis)|(\dter)|(\d\s)|(\da\s)|(\db\s)|(\dbis\s)|(\dter\s)|(\d\sa\s)|(\d\sb\s)|(\d\sbis\s)|(\d\ster\s))\/|((?<!(\d))\s\bet)|(ainsi\sque)|((?<!(\d))\s-\s(?!(bt)|(bis)|(ter)))|(?<!(\d\sa)|(\d\sb)|(\d\sbis)|(\d\ster)|(\d)|(\da)|(\db)|(\dbis)|(\dter)|(\d\s)|(\da\s)|(\db\s)|(\dbis\s)|(\dter\s)|(\d\sa\s)|(\d\sb\s)|(\d\sbis\s)|(\d\ster\s))\+)"
|
|
|
# # Remplacement de chaque séparateur par un pipe ("|")
|
|
|
# subst = "|"
|
|
|
# repl = regex.sub(expr, subst, value, 0, regex.MULTILINE | regex.IGNORECASE)
|
|
|
# # Formattage (supression des espaces insécables et des ":")
|
|
|
# filtered = regex.sub('\\xa0|:', '', repl, 0, regex.MULTILINE | regex.IGNORECASE)
|
|
|
# # Séparation en liste
|
|
|
# splitted = regex.split('\|', filtered, regex.MULTILINE | regex.IGNORECASE)
|
|
|
# # Suppression des espaces en début et fin de chaîne
|
|
|
# stripped = [x.strip() for x in splitted]
|
|
|
# # Suppression des "None" de la liste (failsafe, ne devrait pas être nécessaire)
|
|
|
# value = list(filter(None, stripped))
|
|
|
# return value
|
|
|
|
|
|
# def process_spider_output(self, response, result, spider):
|
|
|
# for r in result:
|
|
|
# adresses = r.pop("adrs")
|
|
|
# adresses = adresses[0]
|
|
|
# indiv = self.splitStreet(adresses)
|
|
|
# index = 0
|
|
|
# for i in indiv:
|
|
|
# d = {"adrs":indiv[index]}
|
|
|
# index += 1
|
|
|
# yield d
|
|
|
|
|
|
|
|
|
|
|
|
class PerilsSpiderMiddleware:
|
|
|
# Not all methods need to be defined. If a method is not defined,
|
|
|
# scrapy acts as if the spider middleware does not modify the
|
|
|
# passed objects.
|
|
|
|
|
|
@classmethod
|
|
|
def from_crawler(cls, crawler):
|
|
|
# This method is used by Scrapy to create your spiders.
|
|
|
s = cls()
|
|
|
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
|
|
return s
|
|
|
|
|
|
def process_spider_input(self, response, spider):
|
|
|
# Called for each response that goes through the spider
|
|
|
# middleware and into the spider.
|
|
|
|
|
|
# Should return None or raise an exception.
|
|
|
return None
|
|
|
|
|
|
def process_spider_output(self, response, result, spider):
|
|
|
# Called with the results returned from the Spider, after
|
|
|
# it has processed the response.
|
|
|
|
|
|
# Must return an iterable of Request, or item objects.
|
|
|
for i in result:
|
|
|
yield i
|
|
|
|
|
|
def process_spider_exception(self, response, exception, spider):
|
|
|
# Called when a spider or process_spider_input() method
|
|
|
# (from other spider middleware) raises an exception.
|
|
|
|
|
|
# Should return either None or an iterable of Request or item objects.
|
|
|
pass
|
|
|
|
|
|
def process_start_requests(self, start_requests, spider):
|
|
|
# Called with the start requests of the spider, and works
|
|
|
# similarly to the process_spider_output() method, except
|
|
|
# that it doesn’t have a response associated.
|
|
|
|
|
|
# Must return only requests (not items).
|
|
|
for r in start_requests:
|
|
|
yield r
|
|
|
|
|
|
def spider_opened(self, spider):
|
|
|
spider.logger.info('Spider opened: %s' % spider.name)
|
|
|
|
|
|
|
|
|
class PerilsDownloaderMiddleware:
|
|
|
# Not all methods need to be defined. If a method is not defined,
|
|
|
# scrapy acts as if the downloader middleware does not modify the
|
|
|
# passed objects.
|
|
|
|
|
|
@classmethod
|
|
|
def from_crawler(cls, crawler):
|
|
|
# This method is used by Scrapy to create your spiders.
|
|
|
s = cls()
|
|
|
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
|
|
return s
|
|
|
|
|
|
def process_request(self, request, spider):
|
|
|
# Called for each request that goes through the downloader
|
|
|
# middleware.
|
|
|
|
|
|
# Must either:
|
|
|
# - return None: continue processing this request
|
|
|
# - or return a Response object
|
|
|
# - or return a Request object
|
|
|
# - or raise IgnoreRequest: process_exception() methods of
|
|
|
# installed downloader middleware will be called
|
|
|
return None
|
|
|
|
|
|
def process_response(self, request, response, spider):
|
|
|
# Called with the response returned from the downloader.
|
|
|
|
|
|
# Must either;
|
|
|
# - return a Response object
|
|
|
# - return a Request object
|
|
|
# - or raise IgnoreRequest
|
|
|
return response
|
|
|
|
|
|
def process_exception(self, request, exception, spider):
|
|
|
# Called when a download handler or a process_request()
|
|
|
# (from other downloader middleware) raises an exception.
|
|
|
|
|
|
# Must either:
|
|
|
# - return None: continue processing this exception
|
|
|
# - return a Response object: stops process_exception() chain
|
|
|
# - return a Request object: stops process_exception() chain
|
|
|
pass
|
|
|
|
|
|
def spider_opened(self, spider):
|
|
|
spider.logger.info('Spider opened: %s' % spider.name)
|
