Homework 7

.gitignore

@@ -0,0 +1,4 @@
+crawls/
+images/
+__pycache__/
+.vscode/

README.md

@@ -1,2 +1,17 @@
-# python_scraping
-Методы сбора и обработки данных из сети Интернет
+# Методы сбора и обработки данных из сети Интернет
+## Урок 7. Парсинг данных. ~~Selenium в Python~~ scrapy
+1) Взять любую категорию товаров на сайте Леруа Мерлен. Собрать следующие данные:
+
+* название;
+* все фото;
+* ссылка;
+* цена.
+
+Реализуйте очистку и преобразование данных с помощью ItemLoader. Цены должны быть в виде числового значения.
+
+Дополнительно:
+
+2) Написать универсальный обработчик характеристик товаров, который будет формировать данные вне зависимости от их типа и количества.
+3) Реализовать хранение скачиваемых файлов в отдельных папках, каждая из которых должна соответствовать собираемому товару
+
+PS: дополнительно реализована обработка ошибки 401 (защита QRATOR CSRF) в middleware и сохранение результатов в базе MongoDB

products/items.py

@@ -0,0 +1,39 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+from scrapy.item import Item, Field
+from itemloaders.processors import MapCompose, TakeFirst, Compose, Identity
+from scrapy.loader import ItemLoader
+import re
+
+def process_price(value):
+    try:
+        return int(re.sub(r'\D+', '', value))
+    except:
+        return value
+
+def process_characteristics(value):
+    result = {}
+    backup = value.copy()
+    try:
+        while value: result |= {value.pop(0): value.pop(0)}
+    except:
+        result = backup
+
+    return result
+
+class ProductsItem(Item):
+    url = Field()
+    name = Field()
+    price = Field()
+    images = Field()
+    characteristics = Field()
+
+class ProductsLoader(ItemLoader):
+    default_output_processor = TakeFirst()
+    price_in = MapCompose(process_price)
+    images_out = Identity()
+    characteristics_in = Compose(process_characteristics)
+    characteristics_out = Identity()

products/middlewares.py

@@ -0,0 +1,154 @@
+# 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, Spider
+from scrapy.http import Request, HtmlResponse
+from scrapy.exceptions import IgnoreRequest
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class ProductsSpiderMiddleware:
+    # 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:HtmlResponse, 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:HtmlResponse, result, spider: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:HtmlResponse, 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):
+        spider.logger.info('Павук открыт: %s' % spider.name)
+
+
+class ProductsDownloaderMiddleware:
+    # 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:Request, spider: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
+        if hasattr(spider, 'state') and isinstance(spider.state, dict):
+            cookies = spider.state.get('cookies')
+            if isinstance(cookies, dict) and cookies and cookies.get('qrator_jsid') != request.cookies.get('qrator_jsid'):
+                request.cookies['qrator_jsid'] = cookies.get('qrator_jsid')
+        return None
+
+    def process_response(self, request:Request, response:HtmlResponse, spider:Spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        if response.status == 401:
+            from urllib.parse import urlparse
+            p = urlparse(response.url)
+            if not p.netloc in ['leroymerlin.ru']:
+                return response
+
+            import requests, re
+            cookies = response.headers.getlist('Set-Cookie')
+            for coo in cookies:
+                if match := re.match('qrator_jsr=(.+?)-(.+?)-', coo.decode('utf-8')):
+                    nonce, qsessid = match.groups()
+                    spider.logger.info('Подбор знаничения pow')
+                    session = requests.Session()
+                    pow = 0
+                    status = 403
+                    while status == 403 and pow < 1280:
+                        if not pow % 10:
+                            print('.', end='', flush=True)
+
+                        pow += 1
+                        url = '%s://%s/__qrator/validate?pow=%s&nonce=%s&qsessid=%s' % (p.scheme, p.netloc, pow, nonce, qsessid)
+                        r = session.post(url, json={})
+                        if (status := r.status_code) == 200: break
+
+                    else:
+                        print()
+                        spider.logger.error('Перебор pow завершился ничем. [%s]' % status)
+                        return response
+
+                    print()
+                    cookies = r.cookies.get_dict()
+                    if qrator_jsid := cookies.get('qrator_jsid'):
+                        spider.logger.info('Значение найдено: pow=%s, qrator_jsid=%s' % (pow, qrator_jsid))
+                        if not (hasattr(spider, 'state') and isinstance(spider.state, dict)):
+                            spider.state = {}
+
+                        if not isinstance(spider.state.get('cookies'), dict):
+                            spider.state['cookies'] = {}
+
+                        spider.state['cookies'].update(cookies)
+
+                        return response.follow(response.url, cookies=request.cookies.update(cookies))
+                    #break # for coo in cookies:
+
+        return response
+
+    def process_exception(self, request, exception, spider: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
+        #spider.logger.info('MIDDLEWARE: process_exception, %s' % request.cookies)
+        pass
+
+    def spider_opened(self, spider:Spider):
+        spider.logger.info('Павук открыт: %s' % spider.name)

products/pipelines.py

@@ -0,0 +1,68 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+import re, os.path
+from itemadapter import ItemAdapter
+from scrapy.pipelines.images import ImagesPipeline
+from scrapy import Request
+from scrapy.spiders import Spider
+from scrapy.exceptions import DropItem
+import pymongo
+
+
+class ProductsPipeline:
+    collection_name = 'scrapy_products'
+
+    def __init__(self, mongo_uri, mongo_db):
+        self.mongo_uri = mongo_uri
+        self.mongo_db = mongo_db
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        return cls(
+            mongo_uri=crawler.settings.get('MONGO_URI'),
+            mongo_db=crawler.settings.get('MONGO_DATABASE', 'products')
+        )
+
+    def open_spider(self, spider:Spider):
+        self.client = pymongo.MongoClient(self.mongo_uri)
+        self.db = self.client[self.mongo_db]
+
+    def close_spider(self, spider:Spider):
+        self.client.close()
+
+    def process_item(self, item, spider:Spider):
+        coll = self.db[self.collection_name]
+        doc = ItemAdapter(item).asdict()
+        #добавляем новые, обновялем старые (upsert=True)
+        if not coll.update_one({'url': doc['url']}, {'$set': doc}, upsert=True).upserted_id:
+            #raise DropItem('Duplicate item found')
+            pass
+
+        return item
+
+class ProductsImagesPipeline(ImagesPipeline):
+    def get_media_requests(self, item, info):
+        if item.get('images'):
+            for img in item['images']:
+                try:
+                    yield Request(img)
+                except Exception as e:
+                    print(e)
+
+    def item_completed(self, results, item, info):
+        item['images'] = [itm[1] for itm in results if itm[0]]
+        return item
+
+    def file_path(self, request, response=None, info=None, *, item=None):
+        try:
+            parts = item['url'].split('/')
+            dir = parts[-1] if parts[-1] else parts[-2]
+        except Exception as e:
+            dir = ''
+
+        return os.path.join(dir, os.path.basename(request.url))

products/settings.py

@@ -0,0 +1,95 @@
+# Scrapy settings for products project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'products'
+
+SPIDER_MODULES = ['products.spiders']
+NEWSPIDER_MODULE = 'products.spiders'
+
+LOG_LEVEL = 'INFO'
+
+#важно
+IMAGES_STORE = 'images'
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 4
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 1.25
+# 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
+#COOKIES_DEBUG = True
+
+# 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://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'products.middlewares.ProductsSpiderMiddleware': 543,
+
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+DOWNLOADER_MIDDLEWARES = {
+    'products.middlewares.ProductsDownloaderMiddleware': 543,
+}
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+    'products.pipelines.ProductsPipeline': 200,
+    'products.pipelines.ProductsImagesPipeline': 100,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.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://docs.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'

products/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.