def parse(self, response):
'''
默认处理start_url地址对应的响应
:param response: response对象
:return: item或者是request
'''
yield Item(response.body)
def parse(self, response):
"""
默认处理start_url地址对应的响应
:param response:
:return:
"""
yield Item(response.body)
def parse(self, response):
"""
解析响应对象
:param response:
:return:
"""
return Item(response.url)
def parse_detail(self, response):
item = response.meta['item']
item['stats-vote'] = response.xpath(
"//span[@class='stats-vote']/i/text()")
item['stats-vote'] = item['stats-vote'][0] if len(
item['stats-vote']) > 0 else None
yield Item(item)
def parse_detail(self, response):
'''解析详情页'''
item = response.meta["item"]
item["url"] = response.url
# print('item：', item) # 打印一下响应的url
# return [] # 由于必须返回一个容器，这里返回一个空列表
yield Item(item) #或者yield Item对象
def parse_detail(self, response):
"""解析详情页数据"""
data = response.meta['data']
# print(data)
data['movie_length'] = response.xpath(
'//span[@property="v:runtime"]/text()')[0]
print(data)
yield 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])
# title_list.apppend(title[0]) # 故意写错,发现程序卡死,没任何提示
yield Item(title_list) # 返回标题
def parse(self, response):
divs = response.xpath('//*[@id="content"]/div/div[1]/ol/li')
for div in divs:
dic = {}
#dic['url'] = response.url
dic['name'] = div.xpath('./div/div[2]/div[1]/a/span[1]/text()')[0]
item = Item(dic)
detail_url = div.xpath('./div/div[2]/div[1]/a/@href')[0]
#yield item
yield Request(detail_url,
callback=self.parse_detail,
meta={'item': item})
def parse(self, response):
"""对响应进行处理"""
# 获取包含电影信息的li标签列表
lis = response.xpath('//*[@id="content"]/div/div[1]/ol/li')
# 遍历lis获取每个电影名
for li in lis:
dic = {'name': li.xpath('./div/div[2]/div[1]/a/span[1]/text()')[0]}
# print(dic)
item = Item(dic)
# 请求详情页，构造详情页的请求
# 1.准备详情的URL
detail_url = li.xpath('./div/div[2]/div[1]/a/@href')[0]
yield Request(detail_url, callback=self.parse_detail, meta={'item': item})
def parse(self, response):
"""
解析响应对象
:param response:
:return:
"""
a_s = response.xpath('//div[@class="hd"]/a')
for a in a_s:
data = {}
data['movie_name'] = a.xpath('./span[1]/text()')[0]
data['movie_url'] = a.xpath('./@href')[0]
# print(data)
# yield Item(data)
# yield Request(data['movie_url'], callback=self.parse_detail, meta={'data': data} )
yield Item(data)
def parse(self, response):
"""提取页面的数据"""
# 先分组，在提取数据
div_list = response.xpath("//div[@id='content-left']/div")
for div in div_list[:1]:
item = {}
item["name"] = div.xpath(".//h2/text()")[0].strip()
item["age"] = div.xpath(
".//div[contains(@class,'articleGender')]/text()")
item["age"] = item["age"][0] if len(item["age"]) > 0 else None
item["gender"] = div.xpath(
".//div[contains(@class,'articleGender')]/@class")
# item["gender"] = item["gender"][0].split(' ')[-1].replace("Icon", "") if len(["gender"]) > 0 else None
item["gender"] = item["gender"][0].split(" ")[-1].replace(
"Icon", "") if len(item["gender"]) > 0 else None
item["href"] = urllib.parse.urljoin(response.url,
div.xpath("./a/@href")[0])
# print(item)
yield Item(item)
yield Request(item["href"],
parse="parse_detail",
meta={"item": item})
def parse(self, response):
'''响应体数据是js代码'''
# 使用js2py模块，执行js代码，获取数据
ret = js2py.eval_js(
response.body.decode("gbk")) # 对网站分析发现，数据编码格式是gbk的，因此需要先进行解码
yield Item(ret.list)
def parse(self, response):
return Item(response.body)
def parse(self, response):
yield Item(response.xpath("//title/text()")[0])
def parse(self, response):
'''
解析请求
并返回新的请求对象、或者数据对象
'''
return Item(response.body) # 返回item对象
def parse_detail(self, response):
item = response.meta['item']
item['stats-vote'] = response.xpath(
"//span[@class='stats-vote']/i/text()")[0]
yield Item(item)
def parse_page(self, response):
"""
处理每个电影详情页的响应
"""
yield Item(response.url)
def parse(self, response):
title_list = response.xpath("//span[@class='title'][1]/text()")
yield Item(title_list)
"""
def parse(self, response):
for node in response.xpath("//div[@class='hd']"):
title = node.xpath(".//span[@class='title'][1]/text()")[0]
yield Item(title)
def parse(self, response):
yield Item(response.body)
def parse(self, response):
"""
解析响应
返回新的请求对象或者数据对象
"""
return Item(response.body)
def parse(self, response):
# 3.对响应数据进行解析，返回数据或新请求
item = Item(response.body)
return item
def parse(self,response):
"""解析"""
yield Item(response.body)
def parse(self, response):
title = response.xpath("//title/text()")[0]
yield Item(title)
def parse_detail(self, response):
"""详情页响应函数"""
item = response.meta["item"]
item["stats_vote"] = response.xpath(
"//span[@class='stats-vote']/i/text()")[0]
yield Item(item)
def parse(self, response):
yield Item(response.url)
def parse_detail(self,response):
item = response.meta.get('item')
item['movie_starring'] = response.xpath('//*[@id="info"]/span[10]/text()')
yield Item(item)
