def parse(self,response):
# 设置编码方式为GBK
response.encoding = 'GBK'
# result=response.re_find_all('{channel\s*:\s*{title\s*:\s*"(.+?)",')
print(response.url)
return Item(response.url)
def parse_detail(self, response):
# 获取上一个解析函数传递过来的数据
data = response.meta['data']
data['movie_length'] = response.xpath(
'//span[@property="v:runtime"]/text()')
# 返回结果
return Item(data)
def parse(self, response):
'''解析豆瓣电影top250列表页'''
title_list = [] # 存储所有的
for li in response.xpath("//ol[@class='grid_view']/li"): # 遍历每一个li标签
title = li.xpath(
".//span[@class='title'][1]/text()") # 提取该li标下的 标题
title_list.append(title[0])
yield Item(title_list)
def parse(self, response):
# item = {}
# item['title'] = response.xpath("//head/title/text()")[0]
# yield Item(item)
node_list = response.xpath("//div[@class='hd']")[:3]
for node in node_list:
item = {}
item['page_title'] = node.xpath("./a/span/text()")[0]
item['page_link'] = node.xpath("./a/@href")[0]
# Item数据，交给管道
yield Item(item)
def parse(self, response):
# item = {}
# item['title'] = response.xpath("//head/title/text()")[0]
# yield Item(item)
node_list = response.xpath("//div[@class='hd']")[:3]
for node in node_list:
item = {}
item['page_title'] = node.xpath("./a/span/text()")[0]
item['page_link'] = node.xpath("./a/@href")[0]
# Item数据，交给管道
yield Item(item)
# Request对象，Engine发送，并由指定的回调函数parse_page解析
yield Request(item['page_link'], callback="parse_page")
def parse_page(self, response):
print("[parse_page] : [{}] <{}>".format(response.status_code,
response.url))
yield Item({})
def parse(self, response):
item = {}
item['title'] = response.xpath("//head/title/text()")[0]
yield Item(item)
def parse_detail(self, response):
data = response.meta['data']
data['movie_length'] = response.xpath(
'//span[@property="v:runtime"]/text()')
return Item(data)
def parse(self, response):
return Item(response.url)