def parse_item(self, response):
item = YdNewsCrawlerItem()
item["create_at"] = get_time_now()
item["update_at"] = get_time_now()
item["topic_id"] = get_id("100")
item["topic_type"] = "101"
item["origin_url"] = response.meta["origin_url"]
# regex = re.compile(r'[^/]*.[jpg|png|gif]$')
for sel in response.xpath("//div[contains(@id, 'container')]"):
item["topic_title"] = sel.xpath("//div//h1/text()").extract()[0]
item["content"] = sel.xpath("//div[contains(@id, 'contentText')]//div//p/text()").extract()
item["image_urls"] = sel.xpath("//td//img/@src").extract()
item["images"] = sel.xpath("//td//img/@src").re(r"[^/]*.[jpg|png|gif]$")
if item["image_urls"]:
yield item
else:
continue
def parse_item(self, response):
item = YdNewsCrawlerItem()
item["create_at"] = get_time_now()
item["update_at"] = get_time_now()
item["topic_id"] = get_id("100")
item["topic_type"] = "102"
item["topic_title"] = response.meta["topic_title"]
item["origin_url"] = response.meta["origin_url"]
for sel in response.xpath("//div[contains(@class, end-text)]//p/text()"):
item["content"] = sel.xpath(".//p/text()").extract()
item["image_urls"] = sel.xpath(".//p//img/@src").extract()
item["images"] = sel.xpath(".//p//img/@src").re(r"[^/]*.[jpg|png|gif]$")
if item["image_urls"]:
yield item
else:
continue
def parse_item(self, response):
item = YdNewsCrawlerItem()
item['create_at'] = get_time_now()
item['update_at'] = get_time_now()
item['topic_id'] = get_id('100')
item['topic_type'] = '103'
item['topic_title'] = response.meta['topic_title']
item['origin_url'] = response.meta['origin_url']
for sel in response.xpath("//div[contains(@class, 'end-text')]"):
item['content'] = sel.xpath(".//p/text()").extract()
item['image_urls'] = sel.xpath(".//p//img/@src").extract()
item['images'] = sel.xpath(".//p//img/@src").re(r'[^/]*.[jpg|png|gif]$')
if item['image_urls']:
yield item
else:
continue
