def parse_item(self, response):
# 使用功能类 itemLoader,以取代 看起来杂乱的 extract() 和 xpath() ，优化如下
i = ItemLoader(item=items.SpideroneItem(), response=response)
# author 作者
# theme 主题
i.add_xpath('author',
'/html/body/div[5]/div[3]/div/a/p[2]/span/span[2]/text()')
i.add_xpath('theme',
'/html/body/div[5]/div[3]/div/a/p[1]/span[1]/text()')
yield i.load_item()
def parse_item(self, response):
i = ItemLoader(item=items.SpideroneItem(), response=response)
i.add_xpath('author',
'/html/body/div[5]/div[3]/div/a/p[2]/span/span[2]/text()')
i.add_xpath('theme',
'/html/body/div[5]/div[3]/div/a/p[1]/span[1]/text()')
res = i.load_item()
print(f"data = {res}")
yield res
def parse(self, response):
str = "asdf.asdf.1.2"
print(str[str.rfind('.'):])
return
# 使用功能类 itemLoader,以取代 看起来杂乱的 extract() 和 xpath() ，优化如下
i = ItemLoader(item=items.SpideroneItem(), response=response)
# author 作者
# theme 主题
i.add_xpath('author','/html/body/div[5]/div[3]/div/a/p[2]/span/span[2]/text()')
i.add_xpath('theme','/html/body/div[5]/div[3]/div/a/p[1]/span[1]/text()')
return i.load_item()
def parse_old2(self, response):
item = items.SpideroneItem()
# author 作者
# theme 主题
author = response.xpath('/html/body/div[5]/div[3]/div/a/p[2]/span/span[2]/text()').extract()
theme = response.xpath('/html/body/div[5]/div[3]/div/a/p[1]/span[1]/text()').extract()
item['author'] = author
item['theme'] = theme
return item
def parse_start_url(self, response):
self.log("++++++++++++++++++++++++++++++++++++")
tt = response.xpath(
'/html/body/div[5]/div[3]/div/a/p[2]/span/span[2]/text()').extract(
)
self.log(tt)
self.log("++++++++++++++++++++++++++++++++++++")
i = ItemLoader(item=items.SpideroneItem(), response=response)
i.add_xpath('author',
'/html/body/div[5]/div[3]/div/a/p[2]/span/span[2]/text()')
i.add_xpath('theme',
'/html/body/div[5]/div[3]/div/a/p[1]/span[1]/text()')
res = i.load_item()
print(f"data = {res}")
yield res