mirror of
https://github.com/Mueller-Patrick/Betterzon.git
synced 2024-12-04 19:45:12 +00:00
26ba21156a
* BETTERZON-58: Basic Functionality with scrapy * Added independent crawler function, yielding price * moved logic to amazon.py * . * moved scrapy files to unused folder * Added basic amazon crawler using beautifulsoup4 * Connected Api to Crawler * Fixed string concatenation for sql statement in getProductLinksForProduct * BETTERZON-58: Fixing SQL insert * BETTERZON-58: Adding access key verification * BETTERZON-58: Fixing API endpoint of the crawler - The list of products in the API request was treated like a string and henceforth, only the first product has been crawled * Added another selector for price on amazon (does not work for books) Co-authored-by: root <root@DESKTOP-ARBPL82.localdomain> Co-authored-by: Patrick Müller <patrick@mueller-patrick.tech> Co-authored-by: Patrick <50352812+Mueller-Patrick@users.noreply.github.com>
104 lines
3.6 KiB
Python
104 lines
3.6 KiB
Python
# 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
|
||
|
||
|
||
class CrawlerSpiderMiddleware:
|
||
# 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 CrawlerDownloaderMiddleware:
|
||
# 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)
|