{"id":370897,"date":"2024-05-21T04:36:01","date_gmt":"2024-05-21T04:36:01","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=370897"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=370897","title":{"rendered":"<span>\u0423\u043f\u043e\u0440\u044f\u0434\u043e\u0447\u0438\u0432\u0430\u0435\u043c \u0437\u0430\u043a\u043b\u0430\u0434\u043a\u0438<\/span>"},"content":{"rendered":"<div><!--[--><!--]--><\/div>\n<div id=\"post-content-body\">\n<div>\n<div class=\"article-formatted-body article-formatted-body article-formatted-body_version-2\">\n<div xmlns=\"http:\/\/www.w3.org\/1999\/xhtml\">\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/5d1\/783\/84a\/5d178384af652d69da206a1f8395dd11.png\" alt=\"\u0417\u0430\u043a\u043b\u0430\u0434\u043a\u0438 \u0438 \u0438\u0445 \u0441\u0442\u0430\u0442\u0438\u0441\u0442\u0438\u043a\u0430\" title=\"\u0417\u0430\u043a\u043b\u0430\u0434\u043a\u0438 \u0438 \u0438\u0445 \u0441\u0442\u0430\u0442\u0438\u0441\u0442\u0438\u043a\u0430\" width=\"1045\" height=\"660\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/5d1\/783\/84a\/5d178384af652d69da206a1f8395dd11.png\"\/><\/p>\n<div><figcaption>\u0417\u0430\u043a\u043b\u0430\u0434\u043a\u0438 \u0438 \u0438\u0445 \u0441\u0442\u0430\u0442\u0438\u0441\u0442\u0438\u043a\u0430<\/figcaption><\/div>\n<\/figure>\n<p>\u0423 \u043c\u0435\u043d\u044f \u043c\u043d\u043e\u0433\u043e \u0441\u0442\u0430\u0442\u0435\u0439 \u0432 \u0437\u0430\u043a\u043b\u0430\u0434\u043a\u0430\u0445. \u041c\u043d\u043e\u0433\u0438\u0435 \u0438\u0437 \u043d\u0438\u0445 \u044f \u0434\u043e\u0431\u0430\u0432\u0438\u043b, \u0447\u0442\u043e\u0431\u044b \u043f\u0440\u043e\u0447\u0438\u0442\u0430\u0442\u044c \u043f\u043e\u0437\u0436\u0435. \u042d\u0442\u0430 \u0441\u0442\u0430\u0442\u044c\u044f \u043d\u0435 \u043f\u0440\u043e \u0442\u043e, \u043f\u043e\u0447\u0435\u043c\u0443 \u0442\u0430\u043a \u043f\u0440\u043e\u0438\u0437\u043e\u0448\u043b\u043e \u0438 \u043a\u0430\u043a \u0441 \u044d\u0442\u0438\u043c \u0431\u043e\u0440\u043e\u0442\u044c\u0441\u044f, \u0430 \u043f\u0440\u043e \u0442\u043e, \u043a\u0430\u043a \u0432\u044b\u0431\u0440\u0430\u0442\u044c \u0441\u0442\u0430\u0442\u044c\u044e \u0434\u043b\u044f <s>\u0443\u0434\u0430\u043b\u0435\u043d\u0438\u044f<\/s> \u0447\u0442\u0435\u043d\u0438\u044f. \u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043d\u0430\u0439\u0434\u0435\u043c \u0441\u0430\u043c\u044b\u0435 \u043b\u0443\u0447\u0448\u0438\u0435 \u0441\u0442\u0430\u0442\u044c\u0438. \u041a\u0440\u0438\u0442\u0435\u0440\u0438\u044f\u043c\u0438 \u043c\u043e\u0433\u0443\u0442 \u0431\u044b\u0442\u044c, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440, \u0440\u0435\u0439\u0442\u0438\u043d\u0433, \u043f\u0440\u043e\u0441\u043c\u043e\u0442\u0440\u044b \u0438 \u0442.\u0434. \u0418 \u043a\u0440\u0430\u0441\u0438\u0432\u043e \u043e\u0444\u043e\u0440\u043c\u0438\u043c \u0432 \u0432\u0438\u0434\u0435 HTML-\u0444\u0430\u0439\u043b\u0430.<\/p>\n<p>\u041f\u0440\u0438\u043c\u0435\u0440 \u0437\u0430\u043a\u043b\u0430\u0434\u043e\u043a <a class=\"mention\" href=\"\/users\/alizar\">@alizar<\/a>: <a href=\"https:\/\/disk.yandex.ru\/d\/e9Jc5gpMEdHnsQ\" rel=\"noopener noreferrer nofollow\">800+ \u0441\u0442\u0430\u0442\u0435\u0439<\/a>.<\/p>\n<h2>\u041a\u0440\u0430\u0442\u043a\u043e<\/h2>\n<ol>\n<li>\n<p><code>$ pip install habra-favorites<\/code> <\/p>\n<\/li>\n<li>\n<p><code>$ habra_favorites &lt;username> # \u0438\u043c\u044f \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044f (\u043d\u0435 \u043e\u0431\u044f\u0437\u0430\u0442\u0435\u043b\u044c\u043d\u043e \u0441\u0432\u043e\u0451)<\/code><\/p>\n<\/li>\n<li>\n<p><code>$ firefox favorites.html # google-chrome favorites.html<\/code> <\/p>\n<\/li>\n<li>\n<p># Hint: \u043d\u0430 \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u044f \u0441\u0442\u043e\u043b\u0431\u0446\u043e\u0432 \u043c\u043e\u0436\u043d\u043e \u043d\u0430\u0436\u0438\u043c\u0430\u0442\u044c, \u0447\u0442\u043e\u0431\u044b \u043f\u0435\u0440\u0435\u0443\u043f\u043e\u0440\u044f\u0434\u043e\u0447\u0438\u0442\u044c.<\/p>\n<\/li>\n<\/ol>\n<h2>\u041f\u043e\u0434\u0440\u043e\u0431\u043d\u0435\u0435<\/h2>\n<p>\u0418\u0441\u0445\u043e\u0434\u043d\u044b\u0439 \u043a\u043e\u0434 \u043f\u0440\u043e\u0435\u043a\u0442\u0430 \u0434\u043e\u0441\u0442\u0443\u043f\u0435\u043d\u00a0<a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\" rel=\"noopener noreferrer nofollow\">GitHub<\/a> \u0438 \u0437\u0430\u043b\u0438\u0442 \u043d\u0430 <a href=\"https:\/\/pypi.org\/project\/habra-favorites\/\" rel=\"noopener noreferrer nofollow\">PyPI<\/a>.<\/p>\n<p>\u0414\u043b\u044f \u043f\u0430\u0440\u0441\u0438\u043d\u0433\u0430 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442\u0441\u044f \u0431\u0438\u0431\u043b\u0438\u043e\u0442\u0435\u043a\u0430\u00a0<a href=\"https:\/\/scrapy.org\" rel=\"noopener noreferrer nofollow\">Scrapy<\/a>. \u0423 \u043d\u0435\u0435 \u043e\u0447\u0435\u043d\u044c \u0445\u043e\u0440\u043e\u0448\u0430\u044f <a href=\"https:\/\/docs.scrapy.org\/en\/latest\/intro\/tutorial.html\" rel=\"noopener noreferrer nofollow\">\u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u0430\u0446\u0438\u044f<\/a>, \u043d\u043e \u043f\u043e\u0437\u0432\u043e\u043b\u044e \u0441\u0435\u0431\u0435 \u043d\u0435\u043c\u043d\u043e\u0433\u043e \u043f\u043e\u0432\u0442\u043e\u0440\u0438\u0442\u044c\u0441\u044f \u0438 \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u044c \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u043e\u043c\u0435\u043d\u0442\u044b.<\/p>\n<h3>Scrapy<\/h3>\n<p>\u0412 Scrapy \u043c\u043d\u0435 \u043d\u0440\u0430\u0432\u0438\u0442\u0441\u044f \u0441\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u043e\u0441\u0442\u044c. \u0421\u043a\u0435\u043b\u0435\u0442 \u043f\u0440\u043e\u0435\u043a\u0442\u0430 \u0447\u0435\u043c-\u0442\u043e \u043f\u043e\u0445\u043e\u0436 \u043d\u0430 \u0441\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0443 \u043f\u0440\u043e\u0435\u043a\u0442\u0430 Django, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u043f\u0440\u0438 \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u0438 \u0431\u0443\u0434\u0443\u0442 \u0432\u043e\u0437\u043d\u0438\u043a\u0430\u0442\u044c \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0441\u043e\u043f\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f.<\/p>\n<h4>Item<\/h4>\n<p>\u041f\u0435\u0440\u0432\u044b\u043c \u0434\u0435\u043b\u043e\u043c \u043e\u0431\u044a\u044f\u0432\u0438\u043c \u043a\u043b\u0430\u0441\u0441 <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/items.py\" rel=\"noopener noreferrer nofollow\">Item<\/a>. Item \u2014 \u044d\u0442\u043e \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u0435 \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u043e\u0432, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u044b \u0431\u0443\u0434\u0435\u0442 \u0441\u043e\u0445\u0440\u0430\u043d\u044f\u0442\u044c. \u0415\u0441\u043b\u0438 \u0433\u043e\u0432\u043e\u0440\u0438\u0442\u044c \u0432 \u0442\u0435\u0440\u043c\u0438\u043d\u0430\u0445 Django, \u0442\u043e \u044d\u0442\u043e Model, \u043d\u0435 \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u0430\u044f \u0441 \u0411\u0414 (\u0445\u043e\u0442\u044f \u044d\u0442\u043e \u043c\u043e\u0436\u043d\u043e \u0434\u043e\u0431\u0430\u0432\u0438\u0442\u044c).<\/p>\n<p>\u0412\u0435\u0440\u043d\u0435\u043c\u0441\u044f \u043a \u043a\u0440\u0438\u0442\u0435\u0440\u0438\u044f\u043c \u0441\u043e\u0440\u0442\u0438\u0440\u043e\u0432\u043a\u0438. \u042d\u0442\u043e \u043a\u0430\u043a \u0440\u0430\u0437 \u0438 \u0431\u0443\u0434\u0443\u0442 \u043f\u043e\u043b\u044f \u043d\u0430\u0448\u0435\u0433\u043e Item: \u0447\u0438\u0441\u043b\u043e\u0432\u044b\u0435 \u0434\u0430\u043d\u043d\u044b\u0435, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u044b \u043c\u043e\u0436\u0435\u043c \u043f\u043e\u043b\u0443\u0447\u0438\u0442\u044c \u0443 \u0441\u0442\u0430\u0442\u044c\u0438. \u041d\u0435 \u0437\u0430\u0431\u0443\u0434\u0435\u043c \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u0435 \u0441 \u0430\u0434\u0440\u0435\u0441\u043e\u043c \u0438 \u0430\u0432\u0442\u043e\u0440\u0430:<\/p>\n<pre><code class=\"python\">class FavoriteItem(Item):     id_ = Field()     ref = Field()     title = Field()     datetime = Field()     author = Field()      # \u0421\u0442\u0430\u0442\u0438\u0441\u0442\u0438\u043a\u0430     rating = Field()  # \u0440\u0435\u0439\u0442\u0438\u043d\u0433     rating_all = Field()  # \u043a\u043e\u043b-\u0432\u043e \u0432\u0441\u0435\u0445 \u0433\u043e\u043b\u043e\u0441\u043e\u0432     rating_up = Field()  # \u043a\u043e\u043b-\u0432\u043e \u0433\u043e\u043b\u043e\u0441\u043e\u0432 \"\u0437\u0430\"     rating_down = Field()  # \u043a\u043e\u043b-\u0432\u043e \u0433\u043e\u043b\u043e\u0441\u043e\u0432 \"\u043f\u0440\u043e\u0442\u0438\u0432\"     views = Field()  # \u043a\u043e\u043b-\u0432\u043e \u043f\u0440\u043e\u0441\u043c\u043e\u0442\u0440\u043e\u0432     count = Field()  # \u043a\u043e\u043b-\u0432\u043e \u0434\u043e\u0431\u0430\u0432\u043b\u0435\u043d\u0438\u0439     comments = Field()  # \u043a\u043e\u043b-\u0432\u043e \u043a\u043e\u043c\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0435\u0432<\/code><\/pre>\n<h3>Loader<\/h3>\n<p>\u0414\u043b\u044f \u0443\u043f\u0440\u043e\u0449\u0435\u043d\u0438\u044f \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u043e\u0432 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u044e\u0442 <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/loaders.py\" rel=\"noopener noreferrer nofollow\">Loader<\/a>&#8216;\u044b. Loader \u043f\u0440\u0438\u043c\u0435\u043d\u044f\u0435\u0442 \u0444\u0443\u043d\u043a\u0446\u0438\u0438 \u0434\u043b\u044f \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u0434\u0430\u043d\u043d\u044b\u0445 \u0438 \u0441\u043e\u0437\u0434\u0430\u0435\u0442 Item. \u041d\u0430\u043f\u043e\u043c\u0438\u043d\u0430\u0435\u0442 \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0443 \u0444\u043e\u0440\u043c \u0432 Django. \u0413\u0434\u0435-\u0442\u043e \u043f\u0440\u043e\u0441\u0442\u043e \u043f\u0440\u0438\u0432\u043e\u0434\u0438\u043c \u043a \u0447\u0438\u0441\u043b\u0443, \u0433\u0434\u0435-\u0442\u043e \u043f\u0438\u0448\u0435\u043c \u0447\u0442\u043e-\u0442\u043e \u0441\u0432\u043e\u0451:  <\/p>\n<pre><code class=\"python\">class FavoriteItemLoader(ItemLoader):     default_item_class = FavoriteItem     default_output_processor = TakeFirst()      id__in = MapCompose(int)     ref_in = MapCompose(urljoin)     datetime_in = MapCompose(process_datetime)     rating_in = MapCompose(process_rating)     rating_all_in = MapCompose(process_rating_all(1))     rating_up_in = MapCompose(process_rating_all(2))     rating_down_in = MapCompose(process_rating_all(3))     views_in = MapCompose(process_views)     count_in = MapCompose(int)     comments_in = MapCompose(int)<\/code><\/pre>\n<h4>Spider<\/h4>\n<p>\u041f\u0435\u0440\u0435\u0445\u043e\u0434\u0438\u043c \u043a \u0441\u0430\u043c\u043e\u043c\u0443 <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/spiders\/favorites_spider.py\" rel=\"noopener noreferrer nofollow\">\u043f\u0430\u0443\u043a\u0443<\/a>. \u041d\u0443\u0436\u043d\u043e \u0441\u043e\u0445\u0440\u0430\u043d\u0438\u0442\u044c \u0441\u0442\u0430\u0442\u044c\u0438 \u0441 \u0442\u0435\u043a\u0443\u0449\u0435\u0439 \u0441\u0442\u0440\u0430\u043d\u0438\u0447\u043a\u0438 \u0438 \u043f\u0435\u0440\u0435\u0439\u0442\u0438 \u043d\u0430 \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0443\u044e, \u0435\u0441\u043b\u0438 \u043e\u043d\u0430 \u0435\u0441\u0442\u044c. \u041d\u0435\u043c\u043d\u043e\u0433\u043e \u0443\u043f\u0440\u043e\u0449\u0435\u043d\u043d\u044b\u0439 \u043a\u043e\u0434:<\/p>\n<pre><code class=\"python\">    def parse(self, response, **kwargs):         if response.status == 404:             msg = 'There is no such user.'             self.logger.error(msg)             raise CloseSpider(msg)          yield from response.follow_all(response.css('a#pagination-next-page'), self.parse)          posts = response.css('article.tm-articles-list__item')         for post in posts:             l = FavoriteItemLoader(selector=post, response=response)              l.add_xpath('id_', '@id')              l.add_css('ref', 'a.tm-title__link::attr(href)')             l.add_css('title', 'a.tm-title__link span::text')             l.add_css('author', 'a.tm-user-info__username::text')             l.add_xpath('datetime', '\/\/time\/@datetime')              l.add_css('rating', '.tm-votes-meter__value_rating::text')             l.add_css('rating_all', '.tm-votes-meter__value_rating::attr(title)')             l.add_css('rating_up', '.tm-votes-meter__value_rating::attr(title)')             l.add_css('rating_down', '.tm-votes-meter__value_rating::attr(title)')             l.add_css('views', '.tm-icon-counter__value::text')             l.add_css('count', '.bookmarks-button__counter::text')             l.add_css('comments', '.tm-article-comments-counter-link__value::text')              yield l.load_item()<\/code><\/pre>\n<h3>Pipeline<\/h3>\n<p>\u0415\u0441\u0442\u044c \u0435\u0449\u0435 \u0443\u0440\u043e\u0432\u0435\u043d\u044c \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0438: <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/pipelines.py\" rel=\"noopener noreferrer nofollow\">Pipeline<\/a>&#8216;\u044b. \u0421\u044e\u0434\u0430 \u043f\u043e\u0441\u0442\u0443\u043f\u0430\u044e\u0442 \u0443\u0436\u0435 \u0441\u043e\u0437\u0434\u0430\u043d\u043d\u044b\u0435 Item&#8217;\u044b. \u0412 \u043f\u0440\u0438\u043d\u0446\u0438\u043f\u0435, \u0434\u0435\u043b\u0430\u0442\u044c \u043c\u043e\u0436\u043d\u043e \u0447\u0442\u043e \u0443\u0433\u043e\u0434\u043d\u043e. \u0418\u043c\u0435\u043d\u043d\u043e \u0437\u0434\u0435\u0441\u044c \u043e\u0431\u044b\u0447\u043d\u043e \u043f\u0440\u043e\u0438\u0441\u0445\u043e\u0434\u0438\u0442 \u0441\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u0435 \u0432 \u0431\u0430\u0437\u0443 \u0438 \u043f\u0440\u043e\u0432\u0435\u0440\u043a\u0430 \u043f\u043e\u043b\u0435\u0439. \u041f\u043e\u0441\u043b\u0435\u0434\u043d\u0438\u043c \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u043e\u043c \u0438 \u0432\u043e\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u043c\u0441\u044f: \u0435\u0441\u043b\u0438 \u0443 \u0441\u0442\u0430\u0442\u044c\u0438 \u043d\u0435\u0442 \u0440\u0435\u0439\u0442\u0438\u043d\u0433\u0430 \u2014 \u0432\u044b\u0441\u0442\u0430\u0432\u0438\u043c None.<\/p>\n<pre><code class=\"python\">class FavoriteItemPipeline(object):      def __init__(self):         self.fields = ['rating', 'rating_all', 'rating_up', 'rating_down']      def process_item(self, item, _spider):         for field in self.fields:             if field not in item:                 item[field] = None         return item<\/code><\/pre>\n<h4>Exporter<\/h4>\n<p>\u0422\u0435\u043f\u0435\u0440\u044c \u043d\u0443\u0436\u043d\u043e \u0432\u0441\u0435 \u0434\u0430\u043d\u043d\u044b\u0435 \u0441\u043e\u0431\u0440\u0430\u0442\u044c \u0432 \u0444\u0430\u0439\u043b. \u0412 Scrapy \u043f\u043e \u0443\u043c\u043e\u043b\u0447\u0430\u043d\u0438\u044e \u0435\u0441\u0442\u044c \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e\u0441\u0442\u044c \u0441\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u044f \u0434\u0430\u043d\u043d\u044b\u0445 \u0432 JSON, XML \u0438 \u0421SV, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u0440\u0435\u0430\u043b\u0438\u0437\u0443\u0435\u0442\u0441\u044f \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e \u043a\u043b\u0430\u0441\u0441\u043e\u0432 Exporter. \u041d\u043e \u044f \u0440\u0435\u0448\u0438\u043b, \u0447\u0442\u043e HTML-\u0441\u0442\u0440\u0430\u043d\u0438\u0447\u043a\u0430, \u0433\u0434\u0435 \u0432\u0438\u0434\u043d\u043e \u0432\u0441\u0435 \u0441\u0442\u0430\u0442\u044c\u0438 \u0441\u043e \u0441\u0441\u044b\u043b\u043a\u0430\u043c\u0438 \u0438 \u043c\u043e\u0436\u043d\u043e \u0432\u0441\u0451 \u0443\u043f\u043e\u0440\u044f\u0434\u043e\u0447\u0438\u0442\u044c, \u043b\u0438\u0448\u044c \u043a\u043b\u0438\u043a\u043d\u0443\u0432 \u043c\u044b\u0448\u043a\u043e\u0439, \u0431\u0443\u0434\u0435\u0442 \u0431\u043e\u043b\u0435\u0435 \u0443\u0434\u043e\u0431\u043d\u044b\u043c \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u043e\u043c. \u0414\u043b\u044f \u044d\u0442\u043e\u0433\u043e \u0431\u044b\u043b \u043d\u0430\u043f\u0438\u0441\u0430\u043d \u043d\u043e\u0432\u044b\u0439 <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/exporters.py\" rel=\"noopener noreferrer nofollow\">Exporter<\/a>.  <\/p>\n<h2>P.S.<\/h2>\n<p>\u041f\u0440\u043e\u0435\u043a\u0442 \u0431\u044b\u043b \u0441\u043e\u0437\u0434\u0430\u043d 11 \u043b\u0435\u0442 \u043d\u0430\u0437\u0430\u0434, \u043a\u043e\u0433\u0434\u0430 \u0435\u0449\u0435 \u0431\u044b\u043b \u0425\u0430\u0431\u0440\u0430\u0445\u0430\u0431\u0440 (\u0438 Geektimes), \u0430 \u0437\u0430\u043a\u043b\u0430\u0434\u043a\u0438 \u0431\u044b\u043b\u0438 \u0438\u0437\u0431\u0440\u0430\u043d\u043d\u044b\u043c. \u041e\u0442\u0441\u044e\u0434\u0430 \u0438 \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u0435.<\/p>\n<\/p>\n<\/div>\n<\/div>\n<\/div>\n<p><!----><!----><\/div>\n<p><!----><\/p>\n<div class=\"tm-article-poll-container\"><!--[--><\/p>\n<div class=\"tm-article-poll tm-article-poll_variant-bordered\">\n<div class=\"tm-notice tm-notice_positive tm-article-poll__notice\"><!----><\/p>\n<div class=\"tm-notice__inner\"><!----><\/p>\n<div class=\"tm-notice__content\" data-test-id=\"notice-content\"><!--[--><span>\u0422\u043e\u043b\u044c\u043a\u043e \u0437\u0430\u0440\u0435\u0433\u0438\u0441\u0442\u0440\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0435 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u043c\u043e\u0433\u0443\u0442 \u0443\u0447\u0430\u0441\u0442\u0432\u043e\u0432\u0430\u0442\u044c \u0432 \u043e\u043f\u0440\u043e\u0441\u0435. <a rel=\"nofollow\" href=\"\/kek\/v1\/auth\/habrahabr\/?back=\/ru\/articles\/800475\/&#038;hl=ru\">\u0412\u043e\u0439\u0434\u0438\u0442\u0435<\/a>, \u043f\u043e\u0436\u0430\u043b\u0443\u0439\u0441\u0442\u0430.<\/span><!--]--><\/div>\n<\/div>\n<\/div>\n<p><!--[--><\/p>\n<div class=\"tm-article-poll__header\">\u041a\u0430\u043a \u043c\u043d\u043e\u0433\u043e \u0441\u0442\u0430\u0442\u0435\u0439 \u0443 \u0432\u0430\u0441 \u0432 \u0437\u0430\u043a\u043b\u0430\u0434\u043a\u0430\u0445?<\/div>\n<div class=\"tm-article-poll__answers\"><!--[--><\/p>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">7.14% <\/span><span class=\"tm-article-poll__answer-label\">&#8212;<\/span><span class=\"tm-article-poll__answer-votes\">2<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 7.14%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">10.71% <\/span><span class=\"tm-article-poll__answer-label\">1-10<\/span><span class=\"tm-article-poll__answer-votes\">3<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 10.71%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">7.14% <\/span><span class=\"tm-article-poll__answer-label\">11-50<\/span><span class=\"tm-article-poll__answer-votes\">2<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 7.14%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">3.57% <\/span><span class=\"tm-article-poll__answer-label\">51-100<\/span><span class=\"tm-article-poll__answer-votes\">1<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 3.57%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">14.29% <\/span><span class=\"tm-article-poll__answer-label\">101-500<\/span><span class=\"tm-article-poll__answer-votes\">4<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 14.29%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">10.71% <\/span><span class=\"tm-article-poll__answer-label\">501-1000<\/span><span class=\"tm-article-poll__answer-votes\">3<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 10.71%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent tm-article-poll__answer-percent_winning\">46.43% <\/span><span class=\"tm-article-poll__answer-label\">1001+<\/span><span class=\"tm-article-poll__answer-votes\">13<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress tm-article-poll__answer-progress_winning\" style=\"width: 46.43%\"><\/div>\n<\/div>\n<\/div>\n<p><!--]--><\/div>\n<div class=\"tm-article-poll__stats\"> \u041f\u0440\u043e\u0433\u043e\u043b\u043e\u0441\u043e\u0432\u0430\u043b\u0438 28 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439.   \u0412\u043e\u0437\u0434\u0435\u0440\u0436\u0430\u043b\u0438\u0441\u044c 5 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439. <\/div>\n<p><!--]--><\/div>\n<p><!--]--><\/div>\n<p> \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 <a href=\"https:\/\/habr.com\/ru\/articles\/800475\/\"> https:\/\/habr.com\/ru\/articles\/800475\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<div><!--[--><!--]--><\/div>\n<div id=\"post-content-body\">\n<div>\n<div class=\"article-formatted-body article-formatted-body article-formatted-body_version-2\">\n<div xmlns=\"http:\/\/www.w3.org\/1999\/xhtml\">\n<figure class=\"full-width\">\n<div><figcaption>\u0417\u0430\u043a\u043b\u0430\u0434\u043a\u0438 \u0438 \u0438\u0445 \u0441\u0442\u0430\u0442\u0438\u0441\u0442\u0438\u043a\u0430<\/figcaption><\/div>\n<\/figure>\n<p>\u0423 \u043c\u0435\u043d\u044f \u043c\u043d\u043e\u0433\u043e \u0441\u0442\u0430\u0442\u0435\u0439 \u0432 \u0437\u0430\u043a\u043b\u0430\u0434\u043a\u0430\u0445. \u041c\u043d\u043e\u0433\u0438\u0435 \u0438\u0437 \u043d\u0438\u0445 \u044f \u0434\u043e\u0431\u0430\u0432\u0438\u043b, \u0447\u0442\u043e\u0431\u044b \u043f\u0440\u043e\u0447\u0438\u0442\u0430\u0442\u044c \u043f\u043e\u0437\u0436\u0435. \u042d\u0442\u0430 \u0441\u0442\u0430\u0442\u044c\u044f \u043d\u0435 \u043f\u0440\u043e \u0442\u043e, \u043f\u043e\u0447\u0435\u043c\u0443 \u0442\u0430\u043a \u043f\u0440\u043e\u0438\u0437\u043e\u0448\u043b\u043e \u0438 \u043a\u0430\u043a \u0441 \u044d\u0442\u0438\u043c \u0431\u043e\u0440\u043e\u0442\u044c\u0441\u044f, \u0430 \u043f\u0440\u043e \u0442\u043e, \u043a\u0430\u043a \u0432\u044b\u0431\u0440\u0430\u0442\u044c \u0441\u0442\u0430\u0442\u044c\u044e \u0434\u043b\u044f <s>\u0443\u0434\u0430\u043b\u0435\u043d\u0438\u044f<\/s> \u0447\u0442\u0435\u043d\u0438\u044f. \u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043d\u0430\u0439\u0434\u0435\u043c \u0441\u0430\u043c\u044b\u0435 \u043b\u0443\u0447\u0448\u0438\u0435 \u0441\u0442\u0430\u0442\u044c\u0438. \u041a\u0440\u0438\u0442\u0435\u0440\u0438\u044f\u043c\u0438 \u043c\u043e\u0433\u0443\u0442 \u0431\u044b\u0442\u044c, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440, \u0440\u0435\u0439\u0442\u0438\u043d\u0433, \u043f\u0440\u043e\u0441\u043c\u043e\u0442\u0440\u044b \u0438 \u0442.\u0434. \u0418 \u043a\u0440\u0430\u0441\u0438\u0432\u043e \u043e\u0444\u043e\u0440\u043c\u0438\u043c \u0432 \u0432\u0438\u0434\u0435 HTML-\u0444\u0430\u0439\u043b\u0430.<\/p>\n<p>\u041f\u0440\u0438\u043c\u0435\u0440 \u0437\u0430\u043a\u043b\u0430\u0434\u043e\u043a <a class=\"mention\" href=\"\/users\/alizar\">@alizar<\/a>: <a href=\"https:\/\/disk.yandex.ru\/d\/e9Jc5gpMEdHnsQ\" rel=\"noopener noreferrer nofollow\">800+ \u0441\u0442\u0430\u0442\u0435\u0439<\/a>.<\/p>\n<h2>\u041a\u0440\u0430\u0442\u043a\u043e<\/h2>\n<ol>\n<li>\n<p><code>$ pip install habra-favorites<\/code> <\/p>\n<\/li>\n<li>\n<p><code>$ habra_favorites &lt;username> # \u0438\u043c\u044f \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044f (\u043d\u0435 \u043e\u0431\u044f\u0437\u0430\u0442\u0435\u043b\u044c\u043d\u043e \u0441\u0432\u043e\u0451)<\/code><\/p>\n<\/li>\n<li>\n<p><code>$ firefox favorites.html # google-chrome favorites.html<\/code> <\/p>\n<\/li>\n<li>\n<p># Hint: \u043d\u0430 \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u044f \u0441\u0442\u043e\u043b\u0431\u0446\u043e\u0432 \u043c\u043e\u0436\u043d\u043e \u043d\u0430\u0436\u0438\u043c\u0430\u0442\u044c, \u0447\u0442\u043e\u0431\u044b \u043f\u0435\u0440\u0435\u0443\u043f\u043e\u0440\u044f\u0434\u043e\u0447\u0438\u0442\u044c.<\/p>\n<\/li>\n<\/ol>\n<h2>\u041f\u043e\u0434\u0440\u043e\u0431\u043d\u0435\u0435<\/h2>\n<p>\u0418\u0441\u0445\u043e\u0434\u043d\u044b\u0439 \u043a\u043e\u0434 \u043f\u0440\u043e\u0435\u043a\u0442\u0430 \u0434\u043e\u0441\u0442\u0443\u043f\u0435\u043d\u00a0<a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\" rel=\"noopener noreferrer nofollow\">GitHub<\/a> \u0438 \u0437\u0430\u043b\u0438\u0442 \u043d\u0430 <a href=\"https:\/\/pypi.org\/project\/habra-favorites\/\" rel=\"noopener noreferrer nofollow\">PyPI<\/a>.<\/p>\n<p>\u0414\u043b\u044f \u043f\u0430\u0440\u0441\u0438\u043d\u0433\u0430 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442\u0441\u044f \u0431\u0438\u0431\u043b\u0438\u043e\u0442\u0435\u043a\u0430\u00a0<a href=\"https:\/\/scrapy.org\" rel=\"noopener noreferrer nofollow\">Scrapy<\/a>. \u0423 \u043d\u0435\u0435 \u043e\u0447\u0435\u043d\u044c \u0445\u043e\u0440\u043e\u0448\u0430\u044f <a href=\"https:\/\/docs.scrapy.org\/en\/latest\/intro\/tutorial.html\" rel=\"noopener noreferrer nofollow\">\u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u0430\u0446\u0438\u044f<\/a>, \u043d\u043e \u043f\u043e\u0437\u0432\u043e\u043b\u044e \u0441\u0435\u0431\u0435 \u043d\u0435\u043c\u043d\u043e\u0433\u043e \u043f\u043e\u0432\u0442\u043e\u0440\u0438\u0442\u044c\u0441\u044f \u0438 \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u044c \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u043e\u043c\u0435\u043d\u0442\u044b.<\/p>\n<h3>Scrapy<\/h3>\n<p>\u0412 Scrapy \u043c\u043d\u0435 \u043d\u0440\u0430\u0432\u0438\u0442\u0441\u044f \u0441\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u043e\u0441\u0442\u044c. \u0421\u043a\u0435\u043b\u0435\u0442 \u043f\u0440\u043e\u0435\u043a\u0442\u0430 \u0447\u0435\u043c-\u0442\u043e \u043f\u043e\u0445\u043e\u0436 \u043d\u0430 \u0441\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0443 \u043f\u0440\u043e\u0435\u043a\u0442\u0430 Django, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u043f\u0440\u0438 \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u0438 \u0431\u0443\u0434\u0443\u0442 \u0432\u043e\u0437\u043d\u0438\u043a\u0430\u0442\u044c \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0441\u043e\u043f\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f.<\/p>\n<h4>Item<\/h4>\n<p>\u041f\u0435\u0440\u0432\u044b\u043c \u0434\u0435\u043b\u043e\u043c \u043e\u0431\u044a\u044f\u0432\u0438\u043c \u043a\u043b\u0430\u0441\u0441 <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/items.py\" rel=\"noopener noreferrer nofollow\">Item<\/a>. Item \u2014 \u044d\u0442\u043e \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u0435 \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u043e\u0432, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u044b \u0431\u0443\u0434\u0435\u0442 \u0441\u043e\u0445\u0440\u0430\u043d\u044f\u0442\u044c. \u0415\u0441\u043b\u0438 \u0433\u043e\u0432\u043e\u0440\u0438\u0442\u044c \u0432 \u0442\u0435\u0440\u043c\u0438\u043d\u0430\u0445 Django, \u0442\u043e \u044d\u0442\u043e Model, \u043d\u0435 \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u0430\u044f \u0441 \u0411\u0414 (\u0445\u043e\u0442\u044f \u044d\u0442\u043e \u043c\u043e\u0436\u043d\u043e \u0434\u043e\u0431\u0430\u0432\u0438\u0442\u044c).<\/p>\n<p>\u0412\u0435\u0440\u043d\u0435\u043c\u0441\u044f \u043a \u043a\u0440\u0438\u0442\u0435\u0440\u0438\u044f\u043c \u0441\u043e\u0440\u0442\u0438\u0440\u043e\u0432\u043a\u0438. \u042d\u0442\u043e \u043a\u0430\u043a \u0440\u0430\u0437 \u0438 \u0431\u0443\u0434\u0443\u0442 \u043f\u043e\u043b\u044f \u043d\u0430\u0448\u0435\u0433\u043e Item: \u0447\u0438\u0441\u043b\u043e\u0432\u044b\u0435 \u0434\u0430\u043d\u043d\u044b\u0435, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u044b \u043c\u043e\u0436\u0435\u043c \u043f\u043e\u043b\u0443\u0447\u0438\u0442\u044c \u0443 \u0441\u0442\u0430\u0442\u044c\u0438. \u041d\u0435 \u0437\u0430\u0431\u0443\u0434\u0435\u043c \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u0435 \u0441 \u0430\u0434\u0440\u0435\u0441\u043e\u043c \u0438 \u0430\u0432\u0442\u043e\u0440\u0430:<\/p>\n<pre><code class=\"python\">class FavoriteItem(Item):     id_ = Field()     ref = Field()     title = Field()     datetime = Field()     author = Field()      # \u0421\u0442\u0430\u0442\u0438\u0441\u0442\u0438\u043a\u0430     rating = Field()  # \u0440\u0435\u0439\u0442\u0438\u043d\u0433     rating_all = Field()  # \u043a\u043e\u043b-\u0432\u043e \u0432\u0441\u0435\u0445 \u0433\u043e\u043b\u043e\u0441\u043e\u0432     rating_up = Field()  # \u043a\u043e\u043b-\u0432\u043e \u0433\u043e\u043b\u043e\u0441\u043e\u0432 \"\u0437\u0430\"     rating_down = Field()  # \u043a\u043e\u043b-\u0432\u043e \u0433\u043e\u043b\u043e\u0441\u043e\u0432 \"\u043f\u0440\u043e\u0442\u0438\u0432\"     views = Field()  # \u043a\u043e\u043b-\u0432\u043e \u043f\u0440\u043e\u0441\u043c\u043e\u0442\u0440\u043e\u0432     count = Field()  # \u043a\u043e\u043b-\u0432\u043e \u0434\u043e\u0431\u0430\u0432\u043b\u0435\u043d\u0438\u0439     comments = Field()  # \u043a\u043e\u043b-\u0432\u043e \u043a\u043e\u043c\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0435\u0432<\/code><\/pre>\n<h3>Loader<\/h3>\n<p>\u0414\u043b\u044f \u0443\u043f\u0440\u043e\u0449\u0435\u043d\u0438\u044f \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u043e\u0432 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u044e\u0442 <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/loaders.py\" rel=\"noopener noreferrer nofollow\">Loader<\/a>&#8216;\u044b. Loader \u043f\u0440\u0438\u043c\u0435\u043d\u044f\u0435\u0442 \u0444\u0443\u043d\u043a\u0446\u0438\u0438 \u0434\u043b\u044f \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u0434\u0430\u043d\u043d\u044b\u0445 \u0438 \u0441\u043e\u0437\u0434\u0430\u0435\u0442 Item. \u041d\u0430\u043f\u043e\u043c\u0438\u043d\u0430\u0435\u0442 \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0443 \u0444\u043e\u0440\u043c \u0432 Django. \u0413\u0434\u0435-\u0442\u043e \u043f\u0440\u043e\u0441\u0442\u043e \u043f\u0440\u0438\u0432\u043e\u0434\u0438\u043c \u043a \u0447\u0438\u0441\u043b\u0443, \u0433\u0434\u0435-\u0442\u043e \u043f\u0438\u0448\u0435\u043c \u0447\u0442\u043e-\u0442\u043e \u0441\u0432\u043e\u0451:  <\/p>\n<pre><code class=\"python\">class FavoriteItemLoader(ItemLoader):     default_item_class = FavoriteItem     default_output_processor = TakeFirst()      id__in = MapCompose(int)     ref_in = MapCompose(urljoin)     datetime_in = MapCompose(process_datetime)     rating_in = MapCompose(process_rating)     rating_all_in = MapCompose(process_rating_all(1))     rating_up_in = MapCompose(process_rating_all(2))     rating_down_in = MapCompose(process_rating_all(3))     views_in = MapCompose(process_views)     count_in = MapCompose(int)     comments_in = MapCompose(int)<\/code><\/pre>\n<h4>Spider<\/h4>\n<p>\u041f\u0435\u0440\u0435\u0445\u043e\u0434\u0438\u043c \u043a \u0441\u0430\u043c\u043e\u043c\u0443 <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/spiders\/favorites_spider.py\" rel=\"noopener noreferrer nofollow\">\u043f\u0430\u0443\u043a\u0443<\/a>. \u041d\u0443\u0436\u043d\u043e \u0441\u043e\u0445\u0440\u0430\u043d\u0438\u0442\u044c \u0441\u0442\u0430\u0442\u044c\u0438 \u0441 \u0442\u0435\u043a\u0443\u0449\u0435\u0439 \u0441\u0442\u0440\u0430\u043d\u0438\u0447\u043a\u0438 \u0438 \u043f\u0435\u0440\u0435\u0439\u0442\u0438 \u043d\u0430 \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0443\u044e, \u0435\u0441\u043b\u0438 \u043e\u043d\u0430 \u0435\u0441\u0442\u044c. \u041d\u0435\u043c\u043d\u043e\u0433\u043e \u0443\u043f\u0440\u043e\u0449\u0435\u043d\u043d\u044b\u0439 \u043a\u043e\u0434:<\/p>\n<pre><code class=\"python\">    def parse(self, response, **kwargs):         if response.status == 404:             msg = 'There is no such user.'             self.logger.error(msg)             raise CloseSpider(msg)          yield from response.follow_all(response.css('a#pagination-next-page'), self.parse)          posts = response.css('article.tm-articles-list__item')         for post in posts:             l = FavoriteItemLoader(selector=post, response=response)              l.add_xpath('id_', '@id')              l.add_css('ref', 'a.tm-title__link::attr(href)')             l.add_css('title', 'a.tm-title__link span::text')             l.add_css('author', 'a.tm-user-info__username::text')             l.add_xpath('datetime', '\/\/time\/@datetime')              l.add_css('rating', '.tm-votes-meter__value_rating::text')             l.add_css('rating_all', '.tm-votes-meter__value_rating::attr(title)')             l.add_css('rating_up', '.tm-votes-meter__value_rating::attr(title)')             l.add_css('rating_down', '.tm-votes-meter__value_rating::attr(title)')             l.add_css('views', '.tm-icon-counter__value::text')             l.add_css('count', '.bookmarks-button__counter::text')             l.add_css('comments', '.tm-article-comments-counter-link__value::text')              yield l.load_item()<\/code><\/pre>\n<h3>Pipeline<\/h3>\n<p>\u0415\u0441\u0442\u044c \u0435\u0449\u0435 \u0443\u0440\u043e\u0432\u0435\u043d\u044c \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0438: <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/pipelines.py\" rel=\"noopener noreferrer nofollow\">Pipeline<\/a>&#8216;\u044b. \u0421\u044e\u0434\u0430 \u043f\u043e\u0441\u0442\u0443\u043f\u0430\u044e\u0442 \u0443\u0436\u0435 \u0441\u043e\u0437\u0434\u0430\u043d\u043d\u044b\u0435 Item&#8217;\u044b. \u0412 \u043f\u0440\u0438\u043d\u0446\u0438\u043f\u0435, \u0434\u0435\u043b\u0430\u0442\u044c \u043c\u043e\u0436\u043d\u043e \u0447\u0442\u043e \u0443\u0433\u043e\u0434\u043d\u043e. \u0418\u043c\u0435\u043d\u043d\u043e \u0437\u0434\u0435\u0441\u044c \u043e\u0431\u044b\u0447\u043d\u043e \u043f\u0440\u043e\u0438\u0441\u0445\u043e\u0434\u0438\u0442 \u0441\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u0435 \u0432 \u0431\u0430\u0437\u0443 \u0438 \u043f\u0440\u043e\u0432\u0435\u0440\u043a\u0430 \u043f\u043e\u043b\u0435\u0439. \u041f\u043e\u0441\u043b\u0435\u0434\u043d\u0438\u043c \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u043e\u043c \u0438 \u0432\u043e\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u043c\u0441\u044f: \u0435\u0441\u043b\u0438 \u0443 \u0441\u0442\u0430\u0442\u044c\u0438 \u043d\u0435\u0442 \u0440\u0435\u0439\u0442\u0438\u043d\u0433\u0430 \u2014 \u0432\u044b\u0441\u0442\u0430\u0432\u0438\u043c None.<\/p>\n<pre><code class=\"python\">class FavoriteItemPipeline(object):      def __init__(self):         self.fields = ['rating', 'rating_all', 'rating_up', 'rating_down']      def process_item(self, item, _spider):         for field in self.fields:             if field not in item:                 item[field] = None         return item<\/code><\/pre>\n<h4>Exporter<\/h4>\n<p>\u0422\u0435\u043f\u0435\u0440\u044c \u043d\u0443\u0436\u043d\u043e \u0432\u0441\u0435 \u0434\u0430\u043d\u043d\u044b\u0435 \u0441\u043e\u0431\u0440\u0430\u0442\u044c \u0432 \u0444\u0430\u0439\u043b. \u0412 Scrapy \u043f\u043e \u0443\u043c\u043e\u043b\u0447\u0430\u043d\u0438\u044e \u0435\u0441\u0442\u044c \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e\u0441\u0442\u044c \u0441\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u044f \u0434\u0430\u043d\u043d\u044b\u0445 \u0432 JSON, XML \u0438 \u0421SV, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u0440\u0435\u0430\u043b\u0438\u0437\u0443\u0435\u0442\u0441\u044f \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e \u043a\u043b\u0430\u0441\u0441\u043e\u0432 Exporter. \u041d\u043e \u044f \u0440\u0435\u0448\u0438\u043b, \u0447\u0442\u043e HTML-\u0441\u0442\u0440\u0430\u043d\u0438\u0447\u043a\u0430, \u0433\u0434\u0435 \u0432\u0438\u0434\u043d\u043e \u0432\u0441\u0435 \u0441\u0442\u0430\u0442\u044c\u0438 \u0441\u043e \u0441\u0441\u044b\u043b\u043a\u0430\u043c\u0438 \u0438 \u043c\u043e\u0436\u043d\u043e \u0432\u0441\u0451 \u0443\u043f\u043e\u0440\u044f\u0434\u043e\u0447\u0438\u0442\u044c, \u043b\u0438\u0448\u044c \u043a\u043b\u0438\u043a\u043d\u0443\u0432 \u043c\u044b\u0448\u043a\u043e\u0439, \u0431\u0443\u0434\u0435\u0442 \u0431\u043e\u043b\u0435\u0435 \u0443\u0434\u043e\u0431\u043d\u044b\u043c \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u043e\u043c. \u0414\u043b\u044f \u044d\u0442\u043e\u0433\u043e \u0431\u044b\u043b \u043d\u0430\u043f\u0438\u0441\u0430\u043d \u043d\u043e\u0432\u044b\u0439 <a href=\"https:\/\/github.com\/ykalchevskiy\/habra-favorites\/blob\/master\/habra_favorites\/exporters.py\" rel=\"noopener noreferrer nofollow\">Exporter<\/a>.  <\/p>\n<h2>P.S.<\/h2>\n<p>\u041f\u0440\u043e\u0435\u043a\u0442 \u0431\u044b\u043b \u0441\u043e\u0437\u0434\u0430\u043d 11 \u043b\u0435\u0442 \u043d\u0430\u0437\u0430\u0434, \u043a\u043e\u0433\u0434\u0430 \u0435\u0449\u0435 \u0431\u044b\u043b \u0425\u0430\u0431\u0440\u0430\u0445\u0430\u0431\u0440 (\u0438 Geektimes), \u0430 \u0437\u0430\u043a\u043b\u0430\u0434\u043a\u0438 \u0431\u044b\u043b\u0438 \u0438\u0437\u0431\u0440\u0430\u043d\u043d\u044b\u043c. \u041e\u0442\u0441\u044e\u0434\u0430 \u0438 \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u0435.<\/p>\n<\/p>\n<\/div>\n<\/div>\n<\/div>\n<p><!----><!----><\/div>\n<p><!----><\/p>\n<div class=\"tm-article-poll-container\"><!--[--><\/p>\n<div class=\"tm-article-poll tm-article-poll_variant-bordered\">\n<div class=\"tm-notice tm-notice_positive tm-article-poll__notice\"><!----><\/p>\n<div class=\"tm-notice__inner\"><!----><\/p>\n<div class=\"tm-notice__content\" data-test-id=\"notice-content\"><!--[--><span>\u0422\u043e\u043b\u044c\u043a\u043e \u0437\u0430\u0440\u0435\u0433\u0438\u0441\u0442\u0440\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0435 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u043c\u043e\u0433\u0443\u0442 \u0443\u0447\u0430\u0441\u0442\u0432\u043e\u0432\u0430\u0442\u044c \u0432 \u043e\u043f\u0440\u043e\u0441\u0435. <a rel=\"nofollow\" href=\"\/kek\/v1\/auth\/habrahabr\/?back=\/ru\/articles\/800475\/&#038;hl=ru\">\u0412\u043e\u0439\u0434\u0438\u0442\u0435<\/a>, \u043f\u043e\u0436\u0430\u043b\u0443\u0439\u0441\u0442\u0430.<\/span><!--]--><\/div>\n<\/div>\n<\/div>\n<p><!--[--><\/p>\n<div class=\"tm-article-poll__header\">\u041a\u0430\u043a \u043c\u043d\u043e\u0433\u043e \u0441\u0442\u0430\u0442\u0435\u0439 \u0443 \u0432\u0430\u0441 \u0432 \u0437\u0430\u043a\u043b\u0430\u0434\u043a\u0430\u0445?<\/div>\n<div class=\"tm-article-poll__answers\"><!--[--><\/p>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">7.14% <\/span><span class=\"tm-article-poll__answer-label\">&#8212;<\/span><span class=\"tm-article-poll__answer-votes\">2<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 7.14%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">10.71% <\/span><span class=\"tm-article-poll__answer-label\">1-10<\/span><span class=\"tm-article-poll__answer-votes\">3<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 10.71%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">7.14% <\/span><span class=\"tm-article-poll__answer-label\">11-50<\/span><span class=\"tm-article-poll__answer-votes\">2<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 7.14%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">3.57% <\/span><span class=\"tm-article-poll__answer-label\">51-100<\/span><span class=\"tm-article-poll__answer-votes\">1<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 3.57%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">14.29% <\/span><span class=\"tm-article-poll__answer-label\">101-500<\/span><span class=\"tm-article-poll__answer-votes\">4<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 14.29%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent\">10.71% <\/span><span class=\"tm-article-poll__answer-label\">501-1000<\/span><span class=\"tm-article-poll__answer-votes\">3<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress\" style=\"width: 10.71%\"><\/div>\n<\/div>\n<\/div>\n<div class=\"tm-article-poll__answer\">\n<div class=\"tm-article-poll__answer-data\"><span class=\"tm-article-poll__answer-percent tm-article-poll__answer-percent_winning\">46.43% <\/span><span class=\"tm-article-poll__answer-label\">1001+<\/span><span class=\"tm-article-poll__answer-votes\">13<\/span><\/div>\n<div class=\"tm-article-poll__answer-bar\">\n<div class=\"tm-article-poll__answer-progress tm-article-poll__answer-progress_winning\" style=\"width: 46.43%\"><\/div>\n<\/div>\n<\/div>\n<p><!--]--><\/div>\n<div class=\"tm-article-poll__stats\"> \u041f\u0440\u043e\u0433\u043e\u043b\u043e\u0441\u043e\u0432\u0430\u043b\u0438 28 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439.   \u0412\u043e\u0437\u0434\u0435\u0440\u0436\u0430\u043b\u0438\u0441\u044c 5 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439. <\/div>\n<p><!--]--><\/div>\n<p><!--]--><\/div>\n<p> \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 <a href=\"https:\/\/habr.com\/ru\/articles\/800475\/\"> https:\/\/habr.com\/ru\/articles\/800475\/<\/a><br \/><\/br><\/br><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-370897","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/370897","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=370897"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/370897\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=370897"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=370897"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=370897"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}