crawl-image-from-http://loza

loza-category.json

@@ -0,0 +1,10 @@
+[
+{"link": "https://loza.vn/ao-so-mi-nu"},
+{"link": "https://loza.vn/quan-cong-so-nu"},
+{"link": "https://loza.vn/vay-dam"},
+{"link": "https://loza.vn/chan-vay"},
+{"link": "https://loza.vn/vest-nu"},
+{"link": "https://loza.vn/ao-khoac-nu"},
+{"link": "https://loza.vn/set-do"},
+{"link": "https://loza.vn/thoi-trang-dao-pho"}
+]

loza/items.py

@@ -0,0 +1,14 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class LozaItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

loza/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class LozaSpiderMiddleware(object):
+    # 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, dict 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 Response, dict
+        # 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 LozaDownloaderMiddleware(object):
+    # 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)

loza/pipelines.py

@@ -0,0 +1,11 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+class LozaPipeline(object):
+    def process_item(self, item, spider):
+        return item

loza/settings.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for loza project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://doc.scrapy.org/en/latest/topics/settings.html
+#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'loza'
+
+SPIDER_MODULES = ['loza.spiders']
+NEWSPIDER_MODULE = 'loza.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'loza (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+#COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'loza.middlewares.LozaSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'loza.middlewares.LozaDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://doc.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'loza.pipelines.LozaPipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

loza/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

loza/spiders/loza_category_spider.py

@@ -0,0 +1,13 @@
+import scrapy
+
+class LozaCategorySpider(scrapy.Spider):
+    name = "loza-category"
+    start_urls = [
+      'https://loza.vn/'
+    ]
+
+    def parse(self, response):
+      for page_link in response.css('#nav ol li a::attr(href)').extract():
+          yield {
+            'link' : page_link
+          }

loza/spiders/loza_dup_spider.py

@@ -0,0 +1,27 @@
+import scrapy
+
+class LozaDupSpider(scrapy.Spider):
+    name = "loza-dup"
+    start_urls = [
+      "https://loza.vn/ao-so-mi-nu",
+      "https://loza.vn/quan-cong-so-nu",
+      "https://loza.vn/vay-dam",
+      "https://loza.vn/chan-vay",
+      "https://loza.vn/vest-nu",
+      "https://loza.vn/ao-khoac-nu",
+      "https://loza.vn/set-do",
+      "https://loza.vn/thoi-trang-dao-pho"
+    ]
+
+    def parse(self, response):
+      for item_link in response.css('div.category-products li.item a.product-image::attr(href)').extract():
+        yield scrapy.Request(item_link, callback=self.parse_single_item)
+
+    def parse_single_item(self, response):
+      for link in response.css('div.more-views ul li a img').xpath('@src').extract():
+        img_link = link.replace("thumbnail/200x280", "image/1000x")
+        yield scrapy.Request(img_link, callback=self.parse_img)
+
+    def parse_img(self, response):
+      with open("dup_image/%s" % response.url.split('/')[-1], 'wb') as f:
+        f.write(response.body)

loza/spiders/loza_spider.py

@@ -0,0 +1,27 @@
+import scrapy
+
+class LozaSpider(scrapy.Spider):
+    name = "loza"
+    start_urls = [
+      "https://loza.vn/ao-so-mi-nu",
+      "https://loza.vn/quan-cong-so-nu",
+      "https://loza.vn/vay-dam",
+      "https://loza.vn/chan-vay",
+      "https://loza.vn/vest-nu",
+      "https://loza.vn/ao-khoac-nu",
+      "https://loza.vn/set-do",
+      "https://loza.vn/thoi-trang-dao-pho"
+    ]
+
+    def parse(self, response):
+      for item_link in response.css('div.category-products li.item a.product-image::attr(href)').extract():
+        yield scrapy.Request(item_link, callback=self.parse_single_item)
+
+    def parse_single_item(self, response):
+      for link in response.css('div.more-views ul li a img').xpath('@src').extract():
+        img_link = link.replace("thumbnail/200x280", "image/1000x")
+        yield scrapy.Request(img_link, callback=self.parse_img)
+
+    def parse_img(self, response):
+      with open("image/%s" % response.url.split('/')[-1], 'wb') as f:
+        f.write(response.body)

loza/spiders/single_item_spider.py

@@ -0,0 +1,18 @@
+import scrapy
+
+class LozaCategorySpider(scrapy.Spider):
+    name = "single-item"
+    start_urls = [
+      'https://loza.vn/ls770-ao-so-mi-hoa-tiet-tay-lung'
+    ]
+
+    def parse(self, response):
+      for link in response.css('div.more-views ul li a img').xpath('@src').extract():
+        img_link = link.replace("thumbnail/200x280", "image/1000x")
+        yield scrapy.Request(img_link, callback=self.parse_img)
+        # yield {
+        #   'link' : link.replace("thumbnail/200x280", "image/1000x")
+        # }
+    def parse_img(self, response):
+      with open("image/%s" % response.url.split('/')[-1], 'wb') as f:
+        f.write(response.body)

scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = loza.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = loza

single-item.json

@@ -0,0 +1,6 @@
+[
+{"link": "https://loza.vn/media/catalog/product/cache/image/1000x/LS770_ao_so_mi_hoa_tiet_2_.jpg"},
+{"link": "https://loza.vn/media/catalog/product/cache/image/1000x/LS770_ao_so_mi_hoa_tiet_3_.jpg"},
+{"link": "https://loza.vn/media/catalog/product/cache/image/1000x/LS770_ao_so_mi_hoa_tiet_1_.png"},
+{"link": "https://loza.vn/media/catalog/product/cache/image/1000x/LS770_ao_so_mi_hoa_tiet_4_.jpg"}
+]