def content(self, response):
item = AoisolasItem()
item['name'] = response.css(".content h5::text").extract_first()
item['ImgUrl'] = response.css(".content-pic img::attr(src)").extract()
yield item
# 提取图片,存入文件夹
# print(item['ImgUrl'])
next_url = response.css(".page-ch:last-child::attr(href)").extract_first()
if next_url is not None:
# 下一页
yield response.follow(next_url, callback=self.content)
def content(self, response):
item = AoisolasItem()
item['name'] = response.css(".bgff h1::text").extract_first()
item['ImgUrl'] = response.css(".pic_tupian img::attr(src)").extract()
item['group'] = response.meta['group']
yield item
# 提取图片,存入文件夹
# print(item['ImgUrl'])
next_url = response.css(
"a:contains('下一页')::attr(href)").extract_first()
next_url = parse.urljoin(response.url, next_url)
if next_url is not None:
# 下一页
yield scrapy.Request(next_url,
callback=self.content,
meta={"group": item['group']})
def content(self, response):
item = AoisolasItem()
data = response.body
soup = BeautifulSoup(data, 'lxml')
title = soup.find('h1', {'class': 'articleV4Tit'}).get_text()
img_url = soup.find('img', {'class': 'IMG_show'}).get('src')
img_urls = []
#titles.append(title)
img_urls.append(img_url)
item['title'] = title
item['ImgUrl'] = img_urls
yield item
next_page = soup.find('a', {'class': 'next-page-a'})
if next_page is not None:
next_page_url = next_page.get('href')
yield response.follow(next_page_url, callback=self.content)