class DartySpider(scrapy.Spider):
name = "darty"
allowed_domains = ["darty.com"]
base_url = "https://www.darty.com"
start_urls = [
base_url + '/nav/extra/list?p=200&s=topa&cat=756'
# base_url + '/nav/extra/list?p=200&s=topa&cat=790',
# base_url + '/nav/extra/list?p=200&s=topa&cat=43554',
# base_url + '/nav/extra/list?p=200&s=topa&cat=12453&fa=17010-135552-42552',
# base_url + '/nav/extra/list?cat=98054&s=prix_asc&p=200&aff=GRID&fa=767'
]
already_crawled = u.get_already_crawled()
def __init__(self):
dispatcher.connect(self.spider_closed, signals.spider_closed)
def spider_closed(self, spider):
u.update_already_crawled(self.already_crawled)
def parse(self, response):
# Yield list pages.
x_pagination = response.xpath(
'//body[@id="darty_liste_produit"]//div[@id="main_pagination_top"]/div['
+ u.x_class('darty_product_list_pages_list') + ']')
if x_pagination:
url_next_page = x_pagination.xpath(
'./a[text()=" Page suivante"][last()]/@href').extract_first()
if url_next_page is not None:
yield Request(self.base_url + url_next_page.strip(),
callback=self.parse)
# Yield product pages.
x_list = response.xpath(
'//body[@id="darty_liste_produit"]//div[@id="main_products_list"]')
if x_list:
urls = x_list.xpath('.//div[' + u.x_class('infos_container') +
']/h2/a/@href').extract()
for url in urls:
url = self.base_url + url.strip()
open_ssl_hash = u.generate_open_ssl_hash(url)
if open_ssl_hash not in self.already_crawled:
self.already_crawled.append(open_ssl_hash)
yield Request(url, callback=self.parse)
# Yield product.
x_product = response.xpath('//body[@id="page_product"]')
if x_product:
item = Product()
# Categories
x_categories = response.xpath('//ul[@id="dartyCom_fil_ariane"]')
main_category = x_categories.xpath(
'./li[2]/a/text()').extract_first()
if main_category is not None:
main_category = main_category.strip()
categories = x_categories.xpath(
'./li[position() >= 3 and position() < last()]/a/text()'
).extract()
if categories:
for i, category in enumerate(categories):
categories[i] = category.strip()
# Brand
brand = response.xpath(
'//a[@id="darty_product_brand"]/text()').extract_first()
if brand is not None:
brand = brand.strip()
# Name
name = re.sub(
' +', ' ', ''.join(
response.xpath('//h1[' + u.x_class('product_head') +
']//div[' + u.x_class('product_name') +
']/span//text()').extract()).replace(
'\n', '').replace('\r', '').strip())
# Price
price, price_old, currency = p.get_darty_prices(response)
# Image
src = response.xpath(
'//div[' +
u.x_class('darty_product_picture_main_pic_container') +
']/div[1]//img/@src').extract_first()
if src is not None:
src = src.strip()
# Avis
x_avis = response.xpath('//div[' +
u.x_class('bloc_reviews_resume') + ']')
rate = x_avis.xpath(
'//meta[@itemprop="ratingValue"]/@content').extract_first()
if rate is not None:
rate = u.string_to_float(rate.strip())
max_rate = x_avis.xpath('//div[' + u.x_class('bloc_reviews_note') +
']/sub/text()').extract_first()
if max_rate is not None:
max_rate = int(re.sub('\D', ' ', max_rate.strip()))
nb_avis = x_avis.xpath(
'//meta[@itemprop="ratingCount"]/@content').extract_first()
if nb_avis is not None:
nb_avis = int(re.sub('\D', ' ', nb_avis.strip()))
item['store'] = self.name
item['url'] = response.url
item['main_category'] = main_category
item['categories'] = categories
item['brand'] = brand
item['openssl_hash'] = u.generate_open_ssl_hash(item['url'])
item['name'] = name
item['price_old'] = price_old
item['price'] = price
item['currency'] = currency
item["image_urls"] = [src]
item["image_name"] = item['openssl_hash']
item["rate"] = rate
item["max_rate"] = max_rate
item["nb_avis"] = nb_avis
item["price_history"] = [{
'date': time.strftime("%Y/%m/%d"),
'price_old': price_old,
'price': price,
'currency': currency
}]
yield item
class FnacSpider(scrapy.Spider):
name = "fnac"
allowed_domains = ["fnac.com"]
base_url = "https://www.fnac.com"
start_urls = [
base_url +
'/Tous-les-ordinateurs-portables/Ordinateurs-portables/nsh154425/w-4?PageIndex=1'
# base_url + '/Tous-les-PC-de-bureau/Ordinateur-de-bureau/nsh51426/w-4?PageIndex=1',
# base_url + '/Toutes-les-tablettes/Toutes-les-tablettes/nsh227099/w-4?PageIndex=1',
# base_url + '/Tous-les-disques-durs/Disque-Dur/nsh119663/w-4?PageIndex=1',
# base_url + '/Memoire-ordinateur-de-bureau/Composants/nsh181559/w-4#bl=MICComposantsARBO',
]
src_no_image = "https://www4-fr.fnac-static.com/Nav/Images/Noscan/noscan_340x340.gif"
already_crawled = u.get_already_crawled()
def __init__(self):
dispatcher.connect(self.spider_closed, signals.spider_closed)
def spider_closed(self, spider):
u.update_already_crawled(self.already_crawled)
def parse(self, response):
# Yield list pages.
x_pagination = response.xpath('//ul[' +
u.x_class('Pager bottom-toolbar') + ']')
if x_pagination:
url_next_page = x_pagination.xpath(
'.//a[' + u.x_class('prevnext actionNext') +
']/@href').extract_first()
if url_next_page is not None:
yield Request(url_next_page, callback=self.parse)
# Yield product pages.
x_list = response.xpath('//ul[' + u.x_class('articleList') + ']')
if x_list:
urls = x_list.xpath('.//p[' + u.x_class('Article-desc') +
']/a/@href').extract()
for url in urls:
open_ssl_hash = u.generate_open_ssl_hash(url)
if open_ssl_hash not in self.already_crawled:
self.already_crawled.append(open_ssl_hash)
yield Request(url, callback=self.parse)
# Yield product.
x_product = response.xpath('//div[' + u.x_class('f-productPage') + ']')
if x_product:
item = Product()
# Categories
x_categories = response.xpath('//ul[' + u.x_class('f-breadcrumb') +
']')
main_category = x_categories.xpath(
'./li[2]/a/text()').extract_first()
if main_category is not None:
main_category = main_category.strip()
categories = x_categories.xpath(
'./li[position() >= 3]/a/text()').extract()
if categories:
for i, category in enumerate(categories):
categories[i] = category.strip()
# Name
name = response.xpath('//h1[' +
u.x_class('f-productHeader-Title') +
']/text()').extract_first().strip()
# Price
price, price_old, currency = p.get_fnac_prices(response)
# Image
src = response.xpath('//img[' +
u.x_class('f-productVisuals-mainMedia') +
']/@src').extract_first()
if src is not None:
src = src.strip()
# Avis
x_avis = response.xpath('//div[' + u.x_class('f-review-header') +
']')
rate = x_avis.xpath('.//div[' + u.x_class('f-review-headerRate') +
']/text()').extract_first()
if rate is not None:
rate = u.string_to_float(rate.strip())
max_rate = x_avis.xpath('.//span[' +
u.x_class('f-review-headerRateTotal') +
']/text()').extract_first()
if max_rate is not None:
max_rate = u.string_to_float(max_rate.strip().replace("/", ""))
nb_avis = response.xpath('//div[' +
u.x_class('f-productHeader-review') +
']//span[' +
u.x_class('f-productHeader-reviewLabel') +
']/text()').extract_first()
if nb_avis is not None:
nb_avis = u.string_to_float(re.sub("\D", "", nb_avis.strip()))
item['store'] = self.name
item['url'] = response.url
item['main_category'] = main_category
item['categories'] = categories
item['brand'] = None
item['openssl_hash'] = u.generate_open_ssl_hash(item['url'])
item['name'] = name
item['price_old'] = price_old
item['price'] = price
item['currency'] = currency
item["image_urls"] = [src]
item["image_name"] = item['openssl_hash']
item["rate"] = rate
item["max_rate"] = max_rate
item["nb_avis"] = nb_avis
item["price_history"] = [{
'date': time.strftime("%Y/%m/%d"),
'price_old': price_old,
'price': price,
'currency': currency
}]
if src == self.src_no_image:
copyfile(
"data/default.jpg", "data/" + self.name + "/img/" +
item["image_name"] + ".jpg")
yield item
class AuchanSpider(scrapy.Spider):
name = "auchan"
allowed_domains = ["auchan.fr"]
base_url = "https://www.auchan.fr"
start_urls = [
base_url + '/informatique/ordinateur-portable/c-7638110'
# base_url + '/informatique/ordinateur-de-bureau/c-7638112',
# base_url + '/informatique/tablette-tactile/c-7328319',
# base_url + '/informatique/stockage/disque-dur-interne/c-6721660',
# base_url + '/informatique/stockage/disque-dur-externe/c-8216',
# base_url + '/informatique/composant-assemblage/barrette-memoire/c-201612291119'
]
already_crawled = u.get_already_crawled()
def __init__(self):
dispatcher.connect(self.spider_closed, signals.spider_closed)
def spider_closed(self, spider):
u.update_already_crawled(self.already_crawled)
def parse(self, response):
# Yield list pages.
x_pagination = response.xpath('//nav[' + u.x_class('ui-pagination') + ']')
if x_pagination:
url_next_page = x_pagination.xpath('.//a[' + u.x_class('ui-pagination--next') + ']/@href').extract_first()
if url_next_page is not None:
yield Request(self.base_url + url_next_page.strip(), callback=self.parse)
# Yield product pages.
x_list = response.xpath('//div[' + u.x_class('product-list--container') + ']')
if x_list:
urls = x_list.xpath('.//div[' + u.x_class('product-item--wrapper') + ']/a/@href').extract()
for url in urls:
url = self.base_url + url.strip()
open_ssl_hash = u.generate_open_ssl_hash(url)
if open_ssl_hash not in self.already_crawled:
self.already_crawled.append(open_ssl_hash)
yield Request(url, callback=self.parse)
# Yield product.
x_product = response.xpath('//div[' + u.x_class('product-detail') + ']')
if x_product:
item = Product()
# Categories
x_categories = response.xpath('//div[' + u.x_class('ui-breadcrumb--scroller') + ']/nav')
main_category = x_categories.xpath('./span[2]/meta[@itemprop="name"]/@content').extract_first()
if main_category is not None:
main_category = main_category.strip()
categories = x_categories.xpath('./span[position() >= 3 and position() < last()]/meta[@itemprop="name"]/@content').extract()
if categories:
for i, category in enumerate(categories):
categories[i] = category.strip()
# Brand
x_brand_name = response.xpath('//div[' + u.x_class('product-detail--wrapper') + ']')
brand = x_brand_name.xpath('./meta[@itemprop="brand"]/@content').extract_first()
if brand is not None:
brand = brand.strip()
# Name
name = x_brand_name.xpath('./h1[' + u.x_class('product-detail--title') + ']/text()').extract_first().replace('\n', '').replace('\r', '').strip()
# Price
price, price_old, currency = p.get_auchan_prices(response)
# Image
src = response.xpath('//div[' + u.x_class('x-scroller') + ']/label[1]//img/@src').extract_first()
if src is not None:
src = src.strip()
# Avis
x_avis = response.xpath('//div[' + u.x_class('product-detail--rating') + ']')
rate = x_avis.xpath('.//meta[@itemprop="ratingValue"]/@content').extract_first()
if rate is not None:
rate = u.string_to_float(rate.strip())
nb_avis = x_avis.xpath('.//meta[@itemprop="reviewCount"]/@content').extract_first()
if nb_avis is not None:
nb_avis = int(nb_avis.strip())
max_rate = x_avis.xpath('.//span[' + u.x_class('ui-rating--background') + ']/i[' + u.x_class('icon-auchan-82') + ']').extract()
max_rate = len(max_rate) if max_rate else None
item['store'] = self.name
item['url'] = response.url
item['main_category'] = main_category
item['categories'] = categories
item['brand'] = brand
item['openssl_hash'] = u.generate_open_ssl_hash(item['url'])
item['name'] = name
item['price_old'] = price_old
item['price'] = price
item['currency'] = currency
item["image_urls"] = [src]
item["image_name"] = item['openssl_hash']
item["rate"] = rate
item["max_rate"] = max_rate
item["nb_avis"] = nb_avis
item["price_history"] = [{'date': time.strftime("%Y/%m/%d"), 'price_old': price_old, 'price': price, 'currency': currency}]
yield item
class CdiscountSpider(scrapy.Spider):
name = "cdiscount"
allowed_domains = ["cdiscount.com"]
base_url = "https://www.cdiscount.com"
start_urls = [
base_url + '/informatique/ordinateurs-pc-portables/pc-portables/l-1070992.html'
# base_url + '/informatique/achat-pc-ordinateur/tous-les-pc-de-bureau/l-1070840.html',
# base_url + '/informatique/disques-durs/disque-dur-externe-ssd/l-1073610.html',
# base_url + '/informatique/disques-durs/disques-durs-externes/l-1073602.html',
# base_url + '/informatique/disques-durs/disque-dur/l-1073632.html',
# base_url + '/informatique/memoire-ram/l-10716.html'
]
first = True
already_crawled = u.get_already_crawled()
nb_crawled = 0
def __init__(self):
dispatcher.connect(self.spider_closed, signals.spider_closed)
def spider_closed(self, spider):
u.update_already_crawled(self.already_crawled)
def parse(self, response):
# Yield list pages.
x_pagination = response.xpath('//ul[@id="PaginationForm_ul"]')
if x_pagination and self.first:
self.first = False
nb_page = x_pagination.xpath('./li[last()]/a/text()').extract_first()
if nb_page is not None:
for x in range(1, int(nb_page.strip())):
yield Request(response.url[:-5] + "-" + str(x) + response.url[-5:], callback=self.parse)
# Yield product pages.
x_list = response.xpath('//ul[@id="lpBloc"]')
if x_list:
urls = x_list.xpath('.//div[' + u.x_class('prdtBILDetails') + ']/a/@href').extract()
for url in urls:
url = url.strip()
open_ssl_hash = u.generate_open_ssl_hash(url)
if open_ssl_hash not in self.already_crawled and self.nb_crawled < 300 :
self.nb_crawled += 1
self.already_crawled.append(open_ssl_hash)
yield Request(url, callback=self.parse)
# Yield product.
x_product = response.xpath('//h1[@itemprop="name"]')
if x_product:
item = Product()
# Categories
x_categories = response.xpath('//div[@id="bc"]')
main_category = x_categories.xpath('.//li[3]//span/text()').extract_first()
if main_category is not None:
main_category = main_category.strip()
categories = x_categories.xpath('.//li[position() >= 4 and position() < last()]//span/text()').extract()
if categories:
for i, category in enumerate(categories):
categories[i] = category.strip()
# Brand
brand = response.xpath('//table[' + u.x_class('fpDescTb fpDescTbPub') + ']//span[@itemprop="brand"]//span[@itemprop="name"]/text()').extract_first()
if brand is not None:
brand = brand.strip()
# Name
name = re.sub(' +', ' ', x_product.xpath('./text()').extract_first().strip())
# Price
price, price_old, currency = p.get_cdiscount_prices(response)
# Image
src = response.xpath('//div[' + u.x_class('fpMainImg') + ']/a[@itemprop="image"]/@href').extract_first()
if src is not None:
src = src.strip()
# Avis
x_avis = response.xpath('//div[' + u.x_class('topMainRating') + ']')
rate = x_avis.xpath('//span[@itemprop="ratingValue"]/text()').extract_first()
if rate is not None:
rate = u.string_to_float(rate.strip())
nb_avis = x_avis.xpath('//span[@itemprop="ratingCount"]/text()').extract_first()
if nb_avis is not None:
nb_avis = int(nb_avis.strip())
item['store'] = self.name
item['url'] = response.url
item['main_category'] = main_category
item['categories'] = categories
item['brand'] = brand
item['openssl_hash'] = u.generate_open_ssl_hash(item['url'])
item['name'] = name
item['price_old'] = price_old
item['price'] = price
item['currency'] = currency
item["image_urls"] = [src]
item["image_name"] = item['openssl_hash']
item["rate"] = rate
item["max_rate"] = 5
item["nb_avis"] = nb_avis
item["price_history"] = [{'date': time.strftime("%Y/%m/%d"), 'price_old': price_old, 'price': price, 'currency': currency}]
yield item
class BoulangerSpider(scrapy.Spider):
name = "boulanger"
allowed_domains = ["boulanger.com"]
base_url = "https://www.boulanger.com"
start_urls = [
base_url + '/c/tous-les-ordinateurs-portables'
# base_url + '/c/tous-les-ordinateurs-de-bureau',
# base_url + '/c/toutes-les-tablettes-tactiles',
# base_url + '/c/disque-dur-externe',
# base_url + '/c/disque-ssd',
# base_url + '/c/memoire-vive'
]
already_crawled = u.get_already_crawled()
def __init__(self):
dispatcher.connect(self.spider_closed, signals.spider_closed)
def spider_closed(self, spider):
u.update_already_crawled(self.already_crawled)
def parse(self, response):
# Yield list pages.
x_pagination = response.xpath('//div[' + u.x_class('navigationListe') +
']')
if x_pagination:
url_next_page = x_pagination.xpath(
'.//span[' + u.x_class('navPage navPage-right') +
']/a/@href').extract_first()
if url_next_page is not None:
yield Request(self.base_url + url_next_page.strip(),
callback=self.parse)
# Yield product pages.
x_list = response.xpath('//div[' + u.x_class('productListe') + ']')
if x_list:
urls = x_list.xpath('.//div[' + u.x_class('designations') +
']/h2/a/@href').extract()
for url in urls:
url = self.base_url + url.strip()
open_ssl_hash = u.generate_open_ssl_hash(url)
if open_ssl_hash not in self.already_crawled:
self.already_crawled.append(open_ssl_hash)
yield Request(url, callback=self.parse)
# Yield product.
x_product = response.xpath('//h1[@itemprop="name"]')
if x_product:
item = Product()
# Categories
x_categories = response.xpath('//div[@id="filAriane"]')
main_category = x_categories.xpath(
'.//li[2]//a/text()').extract_first()
if main_category is not None:
main_category = main_category.strip()
categories = x_categories.xpath(
'.//li[position() >= 3 and position() <= last()]//a/text()'
).extract()
if categories:
for i, category in enumerate(categories):
categories[i] = category.strip()
# Name
name = re.sub(
' +', ' ',
''.join(x_product.xpath('./text()').extract()).replace(
'\n', '').replace('\r', '').strip())
# Price
price, price_old, currency = p.get_boulanger_prices(response)
# Image
src = response.xpath(
'//span[@itemprop="gtin13"]/text()').extract_first()
if src is not None:
src = "https://boulanger.scene7.com/is/image/Boulanger/" + src.strip(
) + "_h_f_l_0"
# Avis
x_avis = response.xpath('//div[' + u.x_class('top') + ']/div[' +
u.x_class('right') + ']//span[' +
u.x_class('rating') + ']')
rate = x_avis.xpath('./@class').extract_first()
if rate is not None:
rate = re.sub('\D', '', rate.strip())
if rate != "0":
if len(rate) > 1:
rate = rate[:1] + "," + rate[1:]
rate = u.string_to_float(rate)
else:
rate = None
nb_avis = x_avis.xpath('./span[' + u.x_class('link') +
']/text()').extract_first()
if nb_avis is not None:
nb_avis = int(re.sub('\D', '', nb_avis.strip()))
item['store'] = self.name
item['url'] = response.url
item['main_category'] = main_category
item['categories'] = categories
item['brand'] = None
item['openssl_hash'] = u.generate_open_ssl_hash(item['url'])
item['name'] = name
item['price_old'] = price_old
item['price'] = price
item['currency'] = currency
item["image_urls"] = [src]
item["image_name"] = item['openssl_hash']
item["rate"] = rate
item["max_rate"] = 5
item["nb_avis"] = nb_avis
item["price_history"] = [{
'date': time.strftime("%Y/%m/%d"),
'price_old': price_old,
'price': price,
'currency': currency
}]
yield item
class MaterielNetSpider(scrapy.Spider):
name = "materiel_net"
allowed_domains = ["materiel.net"]
base_url = "https://www.materiel.net"
start_urls = [
base_url + '/pc-portable/?p=1'
# base_url + '/ordinateur/?p=1',
# base_url + '/tablette-tactile/?p=1',
# base_url + '/disque-ssd/?p=1',
# base_url + '/disque-dur/?p=1',
# base_url + '/disque-dur-externe/?p=1',
# base_url + '/barrette-memoire-pour-pc/?p=1',
# base_url + '/barrette-memoire-pour-pc-portable/?p=1'
]
already_crawled = u.get_already_crawled()
def __init__(self):
dispatcher.connect(self.spider_closed, signals.spider_closed)
def spider_closed(self, spider):
u.update_already_crawled(self.already_crawled)
def parse(self, response):
# Yield list pages.
x_pagination = response.xpath('//ul[' +
u.x_class('pagination pagination-sm') +
']')
if x_pagination:
url_next_page = x_pagination.xpath(
'./li[position() = last()]/a/@href').extract_first()
if url_next_page is None:
url_next_page = x_pagination.xpath(
'./li[position() = (last() - 1)]/a/@href').extract_first()
if url_next_page is not None:
yield Request(self.base_url + url_next_page,
callback=self.parse)
# Yield product pages.
x_list = response.xpath('//table[' + u.x_class('ProdList') + ']')
if x_list:
urls = x_list.xpath('.//td[' + u.x_class('Photo') +
']/span/@data-href').extract()
for url in urls:
url = self.base_url + url
open_ssl_hash = u.generate_open_ssl_hash(url)
if open_ssl_hash not in self.already_crawled:
self.already_crawled.append(open_ssl_hash)
yield Request(url, callback=self.parse)
# Yield product.
x_product = response.xpath('//div[@id="prod"]')
if x_product:
item = Product()
# Categories
x_categories = response.xpath('//nav[@id="breadcrumb"]')
categories = x_categories.xpath(
'.//li[position() >= 3 and position() < last()]/a/text()'
).extract()
if categories:
for i, category in enumerate(categories):
categories[i] = category.strip()
# Brand
brand = x_categories.xpath('.//li[2]/a/text()').extract_first()
if brand is not None:
brand = brand.strip()
# Name
name = re.sub(
' +', ' ', ''.join(
response.xpath(
'//h1[@id="ProdTitle"]//text()').extract()).replace(
'\n', '').replace('\r', '').strip())
# Price
price, price_old, currency = p.get_materiel_net_prices(response)
# Image
src = response.xpath('//div[' + u.x_class('swiper-wrapper') +
']//a/@data-zoom-image').extract_first()
if src is None:
src = response.xpath(
'//div[@id="container-image"]/@data-zoom-image'
).extract_first()
if src is not None:
src = src.strip()
# Avis
x_avis = response.xpath('//div[' + u.x_class('headerAvisClients') +
']')
rate = x_avis.xpath('.//span[' + u.x_class('noteUser') +
']/text()').extract_first()
if rate is not None:
rate = u.string_to_float(rate.strip())
max_rate = x_avis.xpath(
'.//span[' + u.x_class('noteUser') +
']/following-sibling::span[1]/text()').extract_first()
if max_rate is not None:
max_rate = u.string_to_float(max_rate.strip())
nb_avis = x_avis.xpath(
'.//span[@id="avisCount"]/span/text()').extract_first()
if nb_avis is not None:
nb_avis = int(nb_avis.strip())
item['store'] = self.name
item['url'] = response.url
item['main_category'] = "Informatique"
item['categories'] = categories
item['brand'] = brand
item['openssl_hash'] = u.generate_open_ssl_hash(item['url'])
item['name'] = name
item['price_old'] = price_old
item['price'] = price
item['currency'] = currency
item["image_urls"] = [src]
item["image_name"] = item['openssl_hash']
item["rate"] = rate
item["max_rate"] = max_rate
item["nb_avis"] = nb_avis
item["price_history"] = [{
'date': time.strftime("%Y/%m/%d"),
'price_old': price_old,
'price': price,
'currency': currency
}]
yield item