Python FormRequest.meta["large_category"]方法代码示例

# 需要导入模块: from scrapy import FormRequest [as 别名]
# 或者: from scrapy.FormRequest import meta["large_category"] [as 别名]
 def parse(self, response):
     url  = response.url
     if "research" in url:
         categories = response.xpath(".//*[@class='catec']")
         for i in xrange(len(categories)-1):
             large_categories = categories[i].xpath(".//*[@class='fl']")
             large_category_name = clean_text(large_categories.xpath(".//text()").extract()[0].strip())
             mid_categories = categories[i].xpath(".//span")
             for mid_category in mid_categories:
                 mid_category_name = clean_text(mid_category.xpath(".//text()").extract()[0].strip())
                 page_url = mid_category.xpath(".//@href").extract()[0]
                 request = FormRequest(page_url, callback=self._parse_page_research, dont_filter=True)
                 request.meta["large_category"] = large_category_name
                 request.meta["mid_category"] = mid_category_name
                 request.meta["first_url"] = page_url
                 yield request
     elif "free" in url:
         large_categories = response.xpath(".//*[@class='tul2']//h2//a")
         for i in xrange(len(large_categories)):
             large_category_name = clean_text(large_categories[i].xpath(".//text()").extract()[0].strip())
             page_url = large_categories[i].xpath("./@href").extract()[0]
             request = FormRequest(page_url, callback=self._parse_page_free, dont_filter=True)
             request.meta["large_category"] = large_category_name
             request.meta["first_url"] = page_url
             yield request

# 需要导入模块: from scrapy import FormRequest [as 别名]
# 或者: from scrapy.FormRequest import meta["large_category"] [as 别名]
 def _parse_page_free(self, response):
     total_pages = int(clean_text(response.xpath(".//*[@class='pages']//a//text()").extract()[-2].strip()))
     first_url = response.meta["first_url"]
     request = FormRequest(first_url, callback=self._parse_free, dont_filter=True)
     request.meta["large_category"] = response.meta["large_category"]
     yield request
     if total_pages>1:
         for i in xrange(1,total_pages):
             next_page = first_url[:-5] + '-p' + str(i+1) + '.html'
             request = FormRequest(next_page, callback=self._parse_free, dont_filter=True)
             request.meta["large_category"] = response.meta["large_category"]
             yield request

# 需要导入模块: from scrapy import FormRequest [as 别名]
# 或者: from scrapy.FormRequest import meta["large_category"] [as 别名]
 def parse(self, response):
     large_categories = response.xpath(".//*[@class='rptmap']//strong//a")
     for large_category in large_categories:
         large_category_name = clean_text(large_category.xpath("./text()").extract()[0].strip())
         page_url = large_category.xpath("./@href").extract()[0]
         url = urljoin(self.base_url, page_url)
         request = FormRequest(url, callback=self.parse_middle_category, dont_filter=True)
         request.meta["large_category"] = large_category_name
         yield request

# 需要导入模块: from scrapy import FormRequest [as 别名]
# 或者: from scrapy.FormRequest import meta["large_category"] [as 别名]
 def parse_middle_category(self, response):
     mid_categories = response.xpath(".//*[@class='report2']//h2//a")
     for mid_category in mid_categories:
         mid_category_name = clean_text(mid_category.xpath("./text()").extract()[0].strip())
         page_url = mid_category.xpath("./@href").extract()[0]
         url = urljoin(self.base_url, page_url)
         request = FormRequest(url, callback=self._parse_item, dont_filter=True)
         request.meta["large_category"] = response.meta["large_category"]
         request.meta["mid_category"] = mid_category_name
         request.meta["first_url"] = url
         yield request

# 需要导入模块: from scrapy import FormRequest [as 别名]
# 或者: from scrapy.FormRequest import meta["large_category"] [as 别名]
 def parse(self, response):
     large_categories = response.xpath(".//*[@class='shopleft_bt']//a")
     middle_categories = response.xpath(".//*[@class='shopnav2']")
     for i in xrange(len(large_categories)):
         large_category_name = clean_text(large_categories[i].xpath("./text()").extract()[0].strip())
         middle_category_list = middle_categories[i].xpath(".//*[@class='shopleft_wt']")
         for middle_category in middle_category_list:
             middle_category_name = clean_text(middle_category.xpath(".//a/text()").extract())
             page_url = middle_category.xpath(".//a//@href").extract()[0]
             url = urljoin(self.base_url, page_url)
             request = FormRequest(url, callback=self._parse_item, dont_filter=True)
             request.meta["large_category"] = large_category_name
             request.meta["mid_category"] = middle_category_name
             yield request

# 需要导入模块: from scrapy import FormRequest [as 别名]
# 或者: from scrapy.FormRequest import meta["large_category"] [as 别名]
    def _parse_item(self, response):
        reports = response.xpath(".//*[@class='info']")
        if len(reports)>0:
            for report in reports:
                item = IndustryReportSpiderItem()
                item["industry_large_category"] = response.meta["large_category"]
                item["industry_mid_category"] = response.meta["mid_category"]
                item["report_name"] = clean_text(report.xpath(".//h3//a/text()").extract()[0].strip())
                industry_small_chs_name = parseIndustryName(item["report_name"])
                if industry_small_chs_name != None:
                    item["industry_small_chs_name"] = industry_small_chs_name
                page_url = report.xpath(".//@href").extract()[0]
                url = urljoin(self.base_url, page_url)
                item["report_link"] = url
                string =clean_text(report.xpath(" //*[@class='rdate']//span/text()").extract()[0].strip())
                temp = self.parseItem(string)
                if len(temp)==1:
                    item["report_revision_time"] = temp[0][0]
                    item["report_page_count"] = temp[0][1]
                    item["report_graph_count"] = temp[0][2]
                    date, date_precision = parse_date(item["report_revision_time"])
                    item["report_revision_time_standard"] = date.replace(tzinfo=pytz.timezone('Asia/Shanghai'))

                item["source_domain"] = self.allowed_domains[0]
                item["source_name"] = u"中国投资咨询网"
                item["price_free"] = False
                yield item

            if_nextpage = response.xpath(".//*[@class='zw']")

            if len(if_nextpage)>0:
                if (if_nextpage.xpath(".//text()").extract()[-1])==u'下一页': #存在翻页
                    page_url =if_nextpage.xpath(".//@href").extract()[-1]
                    url = urljoin(self.base_url, page_url)
                    request = FormRequest(url, callback=self._parse_item, dont_filter=True)
                    request.meta["large_category"] = response.meta["large_category"]
                    request.meta["mid_category"] = response.meta["mid_category"]
                    yield request

# 需要导入模块: from scrapy import FormRequest [as 别名]
# 或者: from scrapy.FormRequest import meta["large_category"] [as 别名]
    def _parse_item(self, response):
        reports = response.xpath(".//*[@class='img_des']/a")
        if len(reports)>0:
            for report in reports:
                item = IndustryReportSpiderItem()
                item["industry_large_category"] = response.meta["large_category"]
                item["industry_mid_category"] = response.meta["mid_category"]
                item["report_name"] = clean_text(report.xpath("./text()").extract()[0].strip())
                industry_small_chs_name = parseIndustryName(item["report_name"])
                if industry_small_chs_name != None:
                    item["industry_small_chs_name"] = industry_small_chs_name
                page_url = report.xpath(".//@href").extract()[0]
                url = urljoin(self.base_url, page_url)
                item["report_link"] = url
                report_time = self.parseTime(item["report_link"])
                if report_time != None:
                    item["report_revision_time"] = report_time
                item["source_domain"] = self.allowed_domains[0]
                item["source_name"] = u"欧咨网"
                date, date_precision = parse_date(item["report_revision_time"])
                item["report_revision_time_standard"] = date.replace(tzinfo=pytz.timezone('Asia/Shanghai'))
                item["price_free"] = False
                yield item

            if len(response.xpath(".//*[@class='page']//@href"))>1: #存在翻页
                page_len = clean_text(response.xpath(".//*[@class='page']//*[@class='fl_l']/text()").extract()[0].strip())
                nextPageurl = response.xpath(".//*[@class='page']//@href").extract()[-1]
                finds = self.pattern_page.findall(page_len)
                currentPage = finds[0][0]
                totlePage = finds[0][1]
                if currentPage != totlePage:
                    url = urljoin(self.base_url, nextPageurl)
                    request = FormRequest(url, callback=self._parse_item, dont_filter=True)
                    request.meta["large_category"] = response.meta["large_category"]
                    request.meta["mid_category"] = response.meta["mid_category"]
                    yield request