def book_parse(self, response: HtmlResponse):
name = response.xpath('//h1/text()').extract_first()
authors = response.xpath(
"//span[contains(text(), 'Автор:')]/..//a/text()").extract()
interpreter = None
editor = None
publisher = response.xpath(
"//span[contains(text(), 'Издательство:')]/..//a/text()"
).extract_first()
series = response.xpath(
"//span[contains(text(), 'Серия:')]/..//a/text()").extract_first()
isbn = response.xpath(
"//input[contains(@class, 'isbn__code')]/@value").extract_first()
pages = response.xpath(
"//span[contains(text(), 'Количество страниц:')]/..//span[2]/text()"
).extract_first()
price = response.xpath(
"//div[@class='item-actions__price']/b/text()").extract_first()
description = response.xpath(
"//div[contains(@class, 'collapse-panel__panel')]/div[contains(@class, "
"'collapse-panel__text')]//text()").extract()
yield BooksparserItem(source=self.allowed_domains[0],
name=name,
authors=authors,
interpreter=interpreter,
editor=editor,
publisher=publisher,
series=series,
isbn=isbn,
pages=pages,
price=price,
description=description)
def parse_book(self, response: HtmlResponse):
href = response.url
title = response.xpath("//h1/text()").extract_first()
authors = response.xpath(
"//a[@data-event-label='author']/text()").extract()
rate = response.xpath("//div[@id='rate']/text()").extract_first()
genre = response.xpath(
"//div[@id='thermometer-books']/span/a/span/text()").extract()
annotation = response.xpath("//h2[1]/../p/text()").extract_first()
price = response.xpath(
"//span[@class='buying-priceold-val-number']/text()"
).extract_first()
if price is None:
price = response.xpath(
"//span[@class='buying-price-val-number']/text()"
).extract_first()
special_price = response.xpath(
"//span[@class='buying-pricenew-val-number']/text()"
).extract_first()
yield BooksparserItem(href=href,
title=title,
authors=authors,
special_price=special_price,
price=price,
rate=rate,
genre=genre,
annotation=annotation)
def handle_book_data(self, response: HtmlResponse):
book_title = response.xpath(
'//div[@class="prodtitle"]/h1/text()').extract_first()
price = response.xpath(
'//span[@class="buying-pricenew-val-number"]/text()'
).extract_first()
if price is None:
price = response.xpath(
'//span[@class="buying-price-val-number"]/text()'
).extract_first()
initial_price = response.xpath(
'//span[@class="buying-priceold-val-number"]/text()'
).extract_first()
if initial_price is None:
initial_price = price
link = response.request.url
author = response.xpath(
'//a[@data-event-label="author"]/text()').extract_first()
rating = response.xpath('//div[@id="rate"]/text()').extract_first()
yield BooksparserItem(book_title=book_title,
book_price=price,
book_initial_price=initial_price,
book_link=link,
book_author=author,
book_rating=rating)
def handle_book_data(self, response: HtmlResponse):
book_title = response.xpath('//h1[@class="item-detail__title"]/text()').extract_first()
price = response.xpath('//div[@class="item-actions__price"]//b/text()').extract_first()
initial_price = response.xpath('//div[@class="item-actions__price-old"]/text()').extract_first()
if initial_price is None:
initial_price = price
link = response.request.url
author = response.xpath('//a[@class="item-tab__chars-link js-data-link"]/text()').extract_first()
rating = response.xpath('//span[@class="rating__rate-value"]/text()').extract_first()
yield BooksparserItem(book_title=book_title, book_price=price, book_initial_price=initial_price,
book_link=link, book_author=author, book_rating=rating)
def book_parse(self, response: HtmlResponse):
name = response.css("h1::text").extract_first()
link = response.url
author = response.css(
"div.authors a.analytics-click-js::text").extract_first()
basic_price = response.css(
"span.buying-priceold-val-number::text").extract_first()
discount_price = response.css(
"span.buying-pricenew-val-number::text").extract_first()
rating = response.xpath("//div[@id='rate']/text()").extract_first()
yield BooksparserItem(name=name,
link=link,
author=author,
basic_price=basic_price,
discount_price=discount_price,
rating=rating)
print()
def parse_book(self, response:HtmlResponse):
href = response.url
title = response.xpath("//h1/text()").extract_first()
if response.xpath("//div[@class='item-tab__chars-list']/div[1]/span/text()").extract_first() == 'Автор:':
authors = response.xpath("//div[@class='item-tab__chars-list']/div[1]//a/text()").extract()
else:
authors = None
rate = response.xpath("//div[@class='rating']//span[@class='rating__rate-value']/text()").extract_first()
genre = response.xpath("//div[@class='breadcrumbs__list']/div/a/text()").extract()
annotation = response.xpath("//div[@class='text-block-d']/p/text()").extract()
price = response.xpath("//div[@class='item-actions__price-old']/text()").extract_first()
special_price = response.xpath("//div[@class='item-actions__price']/b/text()").extract_first()
yield BooksparserItem(href=href, title=title, authors=authors,
special_price=special_price, price=price, rate=rate,
genre=genre, annotation=annotation)
def book_parse(self, response: HtmlResponse):
name = response.css("h1::text").extract_first()
link = response.url
author = response.css(
"div.js-tab-switcher-item._active a.item-tab__chars-link::text"
).extract_first()
basic_price = response.css(
"div.item-actions__price-old::text").extract_first()
discount_price = response.css(
"div.item-actions__price b::text").extract_first()
rating = response.css("span.rating__rate-value::text").extract_first()
yield BooksparserItem(name=name,
link=link,
author=author,
basic_price=basic_price,
discount_price=discount_price,
rating=rating)
print()
def book_parse(self, response: HtmlResponse):
name = response.xpath('//h1/text()').extract_first()
authors = response.xpath(
"//div[contains(text(), 'Автор:')]/a/text()").extract()
interpreter = response.xpath(
"//div[contains(text(), 'Переводчик:')]/a/text()").extract_first()
editor = response.xpath(
"//div[contains(text(), 'Редактор:')]/a/text()").extract_first()
publisher = response.xpath(
"//div[@class='publisher']/a/text()").extract_first()
series = response.xpath(
"//div[@class='series']/a/text()").extract_first()
isbn = response.xpath("//div[@class='isbn']/text()").extract_first()
pages = response.xpath("//div[@class='pages2']/text()").extract_first()
price = response.xpath(
"//span[@class='buying-pricenew-val-number']/text()"
).extract_first()
description = response.xpath(
"//div[@id='fullannotation']/p//text()").extract_first()
if description is None:
description = response.xpath(
"//div[@id='product-about']/p//text()").extract_first()
if description is None:
description = response.xpath(
"//h2/..//*/p//text()").extract_first()
yield BooksparserItem(source=self.allowed_domains[0],
name=name,
authors=authors,
interpreter=interpreter,
editor=editor,
publisher=publisher,
series=series,
isbn=isbn,
pages=pages,
price=price,
description=description)