def parse(self, response):
li_list = response.xpath('/html/body/div/div[2]/div[4]/ul/li')
for li in li_list:
img_src = li.xpath('./div/a/div/img/@src').extract_first()
item = ImgsproItem()
item['src'] = img_src
yield item
def parse(self, response):
div_list = response.xpath('//div[@id="container"]/div')
for div in div_list:
# 注意：使用伪属性
src = div.xpath('./div/a/img/@src2').extract_first()
item = ImgsproItem()
item['src'] = src
print(item)
yield item
def parse(self, response):
div_list = response.xpath('//div[@id="container"]/div')
for div in div_list:
src = 'https:' + div.xpath('./div/a/img/@src2').get()
item = ImgsproItem()
item['src'] = src
yield item
def parse(self, response):
div_list = response.xpath('//*[@id="container"]/div')
for div in div_list:
#src2伪属性
src = div.xpath('./div/a/img/@src2').extract_first().split('_')[0]
src = 'https:'+ src + '.jpg'
print(src)
item = ImgsproItem()
item['src'] = src
yield item
def parse(self, response):
div_list = response.xpath('//div[@id="container"]/div')
for div in div_list:
# 反爬机制：图片懒加载：当图片被滑动到可视界面时图片地址由 src2 变为 src
#对应：使用伪属性 src2
# src = div.xpath('./div/a/img/@src | ./div/a/img/@src2').extract_first()
src = div.xpath('./div/a/img/@src2').extract_first()
# print(src)
item = ImgsproItem()
item['src'] = src #把src传给 item
yield item
def parse(self, response):
div_list = response.xpath('//div[@id="container"]/div')
for div in div_list:
img_name = div.xpath('./div/a/@alt').extract_first()
# print(img_name)
# 这是一种软加载的模式，只有当前查看的img的属性是src，其它是src2，而这里没有可视化界面，也就是全部都是src2
src = div.xpath('./div/a/img/@src2').extract_first()
# print(src)
item = ImgsproItem()
item['src'] = src
item['img_name'] = img_name
yield item
def parse(self, response):
div_list = response.xpath('//div[@id="container"]/div')
for div in div_list:
# 注意：页面设置了图片懒加载，使用伪属性src2获取图片src
src = div.xpath('./div/a/img/@src2').extract_first()
print(src)
item = ImgsproItem()
item['src'] = src
# 提交item到管道
yield item
def parse(self, response):
#显示请求头信息
print(response.request.headers)
div_list = response.xpath('//div[@id="container"]/div')
for div in div_list:
#注意：使用伪属性
src = div.xpath('./div/a/img/@src2').extract_first()
name = div.xpath('./div/a/img/@alt').extract_first()
item = ImgsproItem()
item['src'] = src
item['name'] = name
yield item
def parse(self, response):
div_list = response.xpath('//*[@id="container"]/div')
# print(div_list)
num = 1
for div in div_list:
# 注意：图片懒加载要使用其伪属性
src = 'https:' + div.xpath('./div/a/img/@src2')[0].extract()
imgName = div.xpath('./div/a/@alt')[0].extract()
print('正在爬取%s: %s' % (imgName, src))
item = ImgsproItem()
item['src'] = src
item['imgName'] = imgName
yield item
if num == 3:
break
num += 1