def parse_item(self, response):
a_list = response.xpath('//a[@class="news14"]')
for a in a_list:
item = FbsproItem()
item['title'] = a.xpath('./text()').extract_first()
yield item
def parse_item(self, response):
# 获取全站标题
li_list = response.xpath('/html/body/div[2]/div[3]/ul[2]/li')
for li in li_list:
title = li.xpath('./span[3]/a/text()').extract_first()
item = FbsproItem()
item['title'] = title
yield item
def parse_item(self, response):
new_list = response.xpath('/html/body/div[8]/table[2]//tr')
for i in new_list:
new_id = i.xpath('./td[1]/text()').extract_first()
new_title = i.xpath('./td[3]/a/text()').extract_first()
item = FbsproItem()
item['new_id'] = new_id
item['new_title'] = new_title
yield item
def parse_item(self, response):
tr_list = response.xpath('/html/body/div[2]/div[3]/ul[2]/li')
for li in tr_list:
id_num = li.xpath('./span/text()').extract_first()
title = li.xpath('./span/a/text()').extract_first()
item = FbsproItem()
item['id_num'] = id_num
item['title'] = title
yield item
def parse_item(self, response):
tr_list = response.xpath(
'//*[@id="morelist"]/div/table[2]//tr/td/table//tr')
for tr in tr_list:
title = tr.xpath('./td[2]/a[2]/@title').extract_first()
status = tr.xpath('./td[3]/span/text()').extract_first()
item = FbsproItem()
item['title'] = title
item['status'] = status
yield item
def parse_item(self, response):
li_lists = response.xpath('/html/body/div[2]/div[3]/ul[2]//li')
for li in li_lists:
new_num = li.xpath(
'./span[@class="state1"]/text()').extract_first()
new_title = li.xpath(
'./span[@class="state3"]/a/text()').extract_first()
item = FbsproItem()
item['title'] = new_title
item['new_num'] = new_num
yield item
def parse_item(self, response):
li_list = response.xpath('/html/body/div[2]/div[3]/ul[2]/li')
for li in li_list:
new_id = li.xpath('./span/text()').extract_first()
new_title = li.xpath('./span[3]//text()').extract_first()
item = FbsproItem()
item['new_id'] = new_id
item['new_title'] = new_title
print(new_id, new_title)
yield item
def parse_item(self, response):
li_list = response.xpath('/html/body/div[2]/div[3]/ul[2]/li')
for li in li_list:
# !!!!xpath中不能出现tbody标签会为空 将tbody标签改成/就好
status = li.xpath('./span[2]/text()').extract_first().split()
title = li.xpath('./span[3]/a/text()').extract_first()
item = FbsproItem()
item['title'] = title
item['status'] = status
yield item
def parse_item(self, response):
tr_list = response.xpath('/html/body/div[8]/table[2]//tr')
for tr in tr_list:
item = FbsproItem()
num = tr.xpath('./td[1]/text()').extract_first()
title = tr.xpath('./td[3]/a/@title').extract_first()
item['num'] = num
item['title'] = title
yield item
def parse_item(self, response):
tr_list = response.xpath(
'//*[@id="morelist"]/div/table[2]//tr/td/table//tr')
for tr in tr_list:
new_num = tr.xpath('./td[1]/text()').extract_first()
new_title = tr.xpath('./td[2]/a[2]/@title').extract_first()
item = FbsproItem()
item['title'] = new_title
item['new_num'] = new_num
yield item
def parse_novel_name(self, response):
# item = {}
# #item['domain_id'] = response.xpath('//input[@id="sid"]/@value').get()
# #item['name'] = response.xpath('//div[su@id="name"]').get()
# #item['description'] = response.xpath('//div[@id="description"]').get()
# return item
print('\n', response)
# 注意：xpath表达式中不可以出现tbody标签
li_list = response.xpath(
'/html/body/div[3]/div/div/div[2]/div[1]/div[2]/ul/li')
for li in li_list:
novel_category = li.xpath('./span[1]/text()').extract_first()
novel_name = li.xpath('./span[2]/a/text()').extract_first()
novel_author = li.xpath('./span[4]/text()').extract_first()
# print(novel_category, novel_name, novel_author)
item = FbsproItem()
item['novel_category'] = novel_category
item['novel_name'] = novel_name
item['novel_author'] = novel_author