def parse(self, response):
baseList=response.xpath('//article/a/text()')
item=DaomuItem()
i=0
for base in baseList:
info=base.extract().split( )
item['title']=info[0]
item['chapter']=info[1]
item['chapterName']=info[2]
item['link']=response.xpath('//article/a/@href').extract()[i]
i+=1
yield item
def parse(self, response):
item = DaomuItem()
item["bookName"] = response.xpath(
'//h1[@class="focusbox-title"]/text()').extract()[0]
articles = response.xpath('//article[@class="excerpt excerpt-c3"]')
for article in articles:
info = article.xpath('./a/text()').extract()[0].split(' ')
item['bookTitle'] = info[0]
item['zhName'] = info[2]
item['zhNum'] = info[1]
item['zhLink'] = article.xpath('./a/@href').extract()[0]
yield item
def parse(self, response):
# 创建item对象（items.py里面的class）
item = DaomuItem()
item["BookName"] = response.xpath(
'//h1[@class="focusbox-title"]/text()').extract()[0]
# 匹配所有章节
articles = response.xpath('//article[@class="excerpt excerpt-c3"]')
for article in articles:
info = article.xpath('./a/text()').extract()[0].split(' ')
# ['七星鲁王','第一章','血尸']
item["BookTitle"] = info[0]
item["zhNum"] = info[1]
item["zhName"] = info[2]
item["zhLink"] = article.xpath('./a/@href').extract()[0]
yield item
def parse(self, response):
# 创建item对象(items.py里的class)
item = DaomuItem()
# 匹配书名，单独匹配
book = response.xpath(
'//h1[@class="focusbox-title"]/text()').extract()[0]
# 匹配所有章节对象(基准xpath)
articles = response.xpath('//article[@class="excerpt excerpt-c3"]')
for article in articles:
info = article.xpath('./a/text()').extract()[0].split(' ')
# ['七星鲁王', '第一章', '血尸']
item["book"] = book
item["title"] = info[0]
item["chapter"] = info[2]
item["chapter_num"] = info[1]
item["chapter_url"] = article.xpath('./a/@href').extract()[0]
yield item
def parse_two_link(self,response):
#基准xpath,匹配所有节点对象的列表
article_list = response.xpath('/html/body/section/div[2]/div/article')
for article in article_list:
# 创建item对象
item = DaomuItem()
info = article.xpath('./a/text()')\
.extract()[0].split()
# info:['七星鲁王','第一章','血尸']
item['va_name'] = info[0]
item['ch_number'] = info[1]
item['ch_name'] = info[2]
item['ch_link'] = article.xpath('./a/@href')\
.extract()[0]
# 将章节链接交给调度器
# 必须把item传递到下一个函数,利用meta参数
yield scrapy.Request(item['ch_link'],
meta={'item':item},
callback= self.parse_three_link)
def parse_two_link(self, response):
# 基准xpath,匹配所有节点对象的列表
article_list = response.xpath('//article[@class="excerpt excerpt-c3"]')
for article in article_list:
# 创建item对象
item = DaomuItem()
info = article.xpath('./a/text()')\
.extract()[0].split()
print(info)
# info:['七星鲁王','第一章,'血尸']
item['va_name'] = info[0]
item['ch_number'] = info[1]
item['ch_name'] = info[2] if len(info) > 2 else ""
item['ch_link'] = article.xpath('./a/@href')\
.extract()[0]
# 将章节链接交给调度器
# 必须把item传递到下一个函数,利用meta参数
yield scrapy.Request(item['ch_link'],
meta={'item': item},
callback=self.parse_three_link)
time.sleep(2)