def parse(self, response):
movie_list = response.xpath(
"//div[@class='article']//ol[@class='grid_view']/li")
for i_item in movie_list:
douban_item = MyfirstpjtItem()
douban_item['serial_number'] = i_item.xpath(
".//div[@class='item']//em/text()").extract_first()
douban_item['movie_name'] = i_item.xpath(
".//div[@class='info']/div[@class='hd']/a/span[1]/text()"
).extract_first()
content = i_item.xpath(
".//div[@class='info']//div[@class='bd']/p[1]/text()").extract(
)
for i_content in content:
content_s = "".join(i_content.split())
douban_item['introduce'] = content_s
douban_item['star'] = i_item.xpath(
".//span[@class='rating_num']/text()").extract_first()
douban_item['evaluate'] = i_item.xpath(
".//div[@class='star']//span[4]//text()").extract_first()
douban_item['describe'] = i_item.xpath(
".//p[@class='quote']/span/text()").extract_first()
# print(douban_item)
yield douban_item
next_link = response.xpath(
"//span[@class='next']/link/@href").extract()
if next_link:
next_link = next_link[0]
yield scrapy.Request("https://movie.douban.com/top250" + next_link,
callback=self.parse)
def parse(self, response):
item = MyfirstpjtItem()
item["urlname"] = response.xpath("/html/head/title/text()")
print("标题：")
print(item["urlname"])
#12.8见myxml
def parse(self, response):
# pass
item = MyfirstpjtItem()
# item['urlname'] = response.xpath('/html/head/title/text()')
# print(item['urlname'])
item['title'] = response.xpath('/html/head/title/text()').extract()
print(item['title'])
def parse(self, response):
item = MyfirstpjtItem()
item["urlname"] = response.xpath("//a[@target='_blank']/text()")
print(item["urlname"])
pass
def parse(self, response):
item = MyfirstpjtItem()
item['urlname'] = response.xpath('/html/head/title/text()')
print("以下将显示网址标题:")
print(item['urlname'])
def parse(self, response):
item=MyfirstpjtItem()
item["urlname"]=response.xpath("/html/head/title/text()")
print("以下将显示爬取的网址的标题")
print(item["urlname"])
def parse(self, response):
item = MyfirstpjtItem()
item['urltitle'] = response.xpath("/html/head/title/text()").extract()
print u"以下将显示爬取的网址的标题"
return item
def parse(self, response):
item = MyfirstpjtItem()
item['urlname'] = response.xpath('/html/head/title/text()').extract()
print('以下将显示爬取的网址的标题')
print(item['urlname'])
return item