Answers for "scrapy itemloader example"

scrapy itemloader example

def parse_question(self, response):
        # ??question??? ??????????question item
        if "QuestionHeader-title" in response.text:
            # ?????
            match_obj = re.match("(.*zhihu.com/question/(\d+))(/|$).*", response.url)
            if match_obj:
                question_id = int(match_obj.group(2))

            item_loader = ItemLoader(item=ZhihuQuestionItem(), response=response)
            item_loader.add_css("title", "h1.QuestionHeader-title::text")
            item_loader.add_css("content", ".QuestionHeader-detail")
            item_loader.add_value("url", response.url)
            item_loader.add_value("zhihu_id", question_id)
            item_loader.add_css("answer_num", ".List-headerText span::text")
            item_loader.add_css("comments_num", ".QuestionHeader-Comment button::text")
            item_loader.add_css("watch_user_num", ".NumberBoard-value::text")
            item_loader.add_css("topics", ".QuestionHeader-topics .Popover div::text")

            question_item = item_loader.load_item()
        else:
            # ????????item??
            match_obj = re.match("(.*zhihu.com/question/(\d+))(/|$).*", response.url)

            if match_obj:
                question_id = int(match_obj.group(2))

            item_loader = ItemLoader(item=ZhihuQuestionItem(), response=response)
            # item_loader.add_css("title", ".zh-question-title h2 a::text")
            item_loader.add_xpath("title",
                                  "//*[@id='zh-question-title']/h2/a/text()|//*[@id='zh-question-title']/h2/span/text()")
            item_loader.add_css("content", "#zh-question-detail")
            item_loader.add_value("url", response.url)
            item_loader.add_value("zhihu_id", question_id)
            item_loader.add_css("answer_num", "#zh-question-answer-num::text")
            item_loader.add_css("comments_num", "#zh-question-meta-wrap a[name='addcomment']::text")
            # item_loader.add_css("watch_user_num", "#zh-question-side-header-wrap::text")
            item_loader.add_xpath("watch_user_num",
                                  "//*[@id='zh-question-side-header-wrap']/text()|//*[@class='zh-question-followers-sidebar']/div/a/strong/text()")
            item_loader.add_css("topics", ".zm-tag-editor-labels a::text")

            question_item = item_loader.load_item()

        yield scrapy.Request(self.start_answer_url.format(question_id, 20, 0), headers=self.headers,
                             callback=self.parse_answer)
        yield question_item

scrapy itemloader example

def parse(self, response):

        for country in response.css(".col-md-4, .country"):
            item = ItemLoader(item=CountryItem(), selector=country)

            item.add_css("country", ".country-name")
            item.add_css("capital", ".country-capital::text")
            item.add_css("population", ".country-population::text")
            item.add_css("area", ".country-area::text")

            yield item.load_item()

scrapy itemloader example

def parse_news_metro(self, response):
        loader = ItemLoader(item=News(), response=response)
        loader.add_value('url', response.url)

        date_selector = response.css('.artikel > div.block-tanggal::text')
        if not date_selector:
            return self.parse_news_pilkada(loader, response)
        try:
            date_time_str = date_selector.extract()[0].split(',')[1].strip()[:-4]
            date_time_str = ' '.join([_(x) for x in date_time_str.split(' ')])
            published_at_wib = datetime.strptime(date_time_str, '%d %B %Y | %H:%M')
        except Exception:
            return loader.load_item()
        published_at = wib_to_utc(published_at_wib)
        if (self.media['last_scraped_at'] >= published_at):
            is_no_update = True
            self.logger.info('Media have no update')
            raise CloseSpider('finished')
        loader.add_value('published_at', published_at)

        title_selector = response.css('.artikel > h1::text')
        if not title_selector:
            return loader.load_item()
        loader.add_value('title', title_selector.extract()[0])

        # Select all p which don't have iframe inside it
        raw_content_selector = response.xpath('//div[@class="artikel"]//p[not(iframe)]')
        if not raw_content_selector:
            return loader.load_item()
        raw_content = ''
        for rsl in raw_content_selector:
            raw_content = raw_content + rsl.extract().strip()

        # Go to next page while there is next page button
        next_page_selector = response.css('.pagination-nb').xpath('//a[text()="next"]/@href')
        if next_page_selector:
            return Request(next_page_selector.extract()[0], callback=lambda x, loader=loader, raw_content=raw_content: self.parse_next_page_metro(x, loader, raw_content))

        loader.add_value('raw_content', raw_content)

        # The author usually put inside <strong> tag, however, some news is not using <strong> tag.
        # NOTE: this block of code may need revision in the future
        author_name = ''
        for author_name_selector in reversed(raw_content_selector):
            author_name_selector = author_name_selector.css('strong::text')
            for tmp in reversed(author_name_selector.extract()):
                tmp = tmp.strip()
                if tmp and all((x.isalpha() and x.isupper()) or x.isspace() or x == '.' or x == '|' for x in tmp):
                    author_name = tmp
                    break
            if author_name:
                break
        author_name = ','.join(author_name.split(' | '))
        loader.add_value('author_name', author_name)
        return loader.load_item()

scrapy itemloader example

def join_tags(value):
    return ','.join([i for i in value if i])


# ??ItemLoader????output_processor??
# ItemLoader????list??????????????????output_processor

scrapy itemloader example

def parse_question(self, response):
        question_pattern = re.compile('(.*zhihu.com/question/(\d+))(/|$).*')
        match_object = re.match(question_pattern, response.url)
        question_id = match_object.group(2)
        item_loader = ItemLoader(item=ZhihuQuestionItem(), response=response)
        item_loader.add_value('zhihu_id', question_id)
        item_loader.add_css('title', 'h1.QuestionHeader-title::text')
        item_loader.add_css('topics', '.TopicLink .Popover div::text')
        item_loader.add_value('url', response.url)
        item_loader.add_css('content', '.QuestionHeader-detail div div span::text')
        item_loader.add_css('answer_num', '.List-headerText span::text')
        item_loader.add_css('comments_num', '.QuestionHeader-Comment button::text')
        item_loader.add_css('watch_user_num', '.NumberBoard-value::text')

        item = item_loader.load_item()
        yield item
        yield scrapy.Request(self.start_answer_url.format(question_id=question_id, offset=0, limit=20),
                             headers=self.headers, callback=self.parse_answer)

scrapy itemloader example

def parse(self, response):
        l = ItemLoader(item=PlantItem(), response=response)

        l.add_xpath('name', "//div[@id='bodycontent']/div[@class='post']/div[@class='pagebanner']/h2/text()")
        l.add_xpath('species', "//div[@id='bodycontent']/div[@class='post']/div[@class='pagebanner']/div[@class='clear resultSpecies']/text()")
        l.add_xpath('key', "//div[@id='bodycontent']/div[@class='post']/div[@class='contents']/div[@id='tabbedinfo']/div[@class='tabscontain']/div[@class='tabs']/div[@class='post-meta']/div[@class='post-meta-key']/text()")
        l.add_xpath('value', "//div[@id='bodycontent']/div[@class='post']/div[@class='contents']/div[@id='tabbedinfo']/div[@class='tabscontain']/div[@class='tabs']/div[@class='post-meta']/div[@class='post-meta-value']/child::node()")
        # l.add_xpath('value', "//div[@id='bodycontent']/div[@class='post']/div[@class='contents']/div[@id='tabbedinfo']/div[@class='tabscontain']/div[@class='tabs']/div[@class='post-meta']/div[@class='post-meta-value']/a/text()")

        return l.load_item()

scrapy itemloader example

def parse_item(self, response):
		l = ItemLoader(item=PageItem(), response=response)
		l.add_value('title', response.request.cookies['title'])
		l.add_value('name', self.name)
		l.add_value('url', response.url)
		l.add_xpath('image_urls', '//td[@valign="top"]/img/@src')
		return l.load_item()

scrapy itemloader example

def parse_item(self, response):

        loader = ItemLoader(GaokaopaiZhiyeItem(), response)
        loader.add_value('url', response.url)
        loader.add_value('code', response.url, re=ur'-([^-]+)\.html')
        loader.add_css('name', u'.modTitle>h1::text')

        def parse_category():
            for e in response.css(u'.catType>a'):
                yield {
                    'url': e.css('::attr(href)').extract_first(),
                    'code': e.css('::attr(href)').re_first(ur'-([^-]+)\.html'),
                    'name': e.css('::text').extract_first(),
                }

        loader.add_value('category', list(parse_category()))
        loader.add_css('detail', u'.zhiyeShow')

        item = loader.load_item()

        return FormRequest(
            url='http://www.gaokaopai.com/ajax-career-getRelateMajor.html',
            formdata={'code': item['code'][0]},
            meta={'item': item},
            dont_filter=True,
            callback=self.parse_majors
        )

scrapy itemloader example

def parse(self, response):
        l = ItemLoader(item=Area(), response=response)
        l.add_value('id', parse_qs(response.xpath('//div[@class="clearfix subnav level-1"]//li//a[2]/@href').extract()[0])['area_id'][0])
        l.add_xpath('name', '//div[@class="clearfix subnav level-1"]//li//a[2]/text()')
        l.add_value('updated', datetime.utcnow().isoformat()) # you can also use literal values
        return l.load_item()
        #self.log('URL: {}'.format(response.url))

scrapy itemloader example

def parse_song_list(self, response):
        selector = Selector(response)

        song_name_list = selector.xpath('//body//ul[@class="f-hide"]/li/a/text()').extract()
        song_id_list = selector.xpath('//body//ul[@class="f-hide"]/li/a/@href').extract()
        title = selector.xpath('//title/text()').extract()
        for index, id_ in enumerate(song_id_list):
            l = ItemLoader(item=PlayListItem())
            l.add_value('song_name', song_name_list[index])
            l.add_value('title', title)
            yield scrapy.FormRequest(url=self.BASE_URL + id_, meta={'song_id': id_[9:], 'loader': l}, method='GET',
                                     headers=self.headers, callback=self.parse_single_song)