def parse(self, response):
"""
得到解析的页面数据
:param response:
:return:
"""
# 调用xpath解析
div_list = response.xpath('//div[@id="content-left"]/div')
# 存储解析到的页面数据到列表中
data_list = []
for div in div_list:
# xpath 解析到的指定内容被存储到Selector对象中
# extract() 方法可以将Selector对象中存储的数据值拿到
# title = div.xpath('./div/a[2]/h2/text()').extract()[0]
title = div.xpath('./div/a[2]/h2/text()').extract_first()
content = div.xpath(
'.//div[@class="content"]/span/text()').extract()[0]
# print(title,content)
dict = {'author': title, 'content': content}
data_list.append(dict)
# 1.将解析到的数据值( author 和 content ) 存储到 items 对象中
item = QiubaiproItem()
item['author'] = title
item['content'] = content
print(content)
# 2.将item 对象提交给管道
yield item
def parse(self, response):
div_list = response.xpath('//div[@class="col1 old-style-col1"]/div')
for div in div_list:
author = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
content = div.xpath('./a[1]/div/span//text()').extract()
content = ''.join(content)
item = QiubaiproItem()
item['author'] = author
item['content'] = content
yield item #将item提交给了管道
def parse(self, response):
li_list = response.xpath('//*[@id="content"]/div/div[2]/div/ul/li')
# print(li_list)
# all_data = []
for li in li_list:
author = li.xpath('./div/div/a/span/text()').extract_first()
content = li.xpath('./div/a/text()').extract_first()
item = QiubaiproItem()
item['author'] = author
item['content'] = content
yield item
def parse(self, response):
div_list = response.xpath('//div[@class="col1 old-style-col1"]/div')
# 存储所有解析到的数据
all_data = []
for div in div_list:
author = div.xpath('./div[1]/a[1]/img/@alt').extract()[0]
content = div.xpath('./a[1]/div/span//text()').extract()
content = ''.join(content)
item = QiubaiproItem()
item['author'] = author
item['content'] = content
# 将item提交给管道
yield item
def parse(self, response):
div_list = response.xpath('//*[@id="content"]/div/div[2]/div')
for div in div_list:
# xpath返回的是列表，但是列表元素一定是Selector类型的对象
# extract可以将Selector对象中data参数存储的字符串提取出来
author = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
# 列表调用了extract之后，则表示将列表中每一个Selector对象中data对应的字符串提取了出来,返回一个列表
content = div.xpath('./a/div/span//text()').extract()
content = ''.join(content)
item = QiubaiproItem()
item['author'] = author
item['content'] = content
# 将item提交给管道
yield item
def parse(self, response):
div_list = response.xpath('//*[@id="content-left"]/div')
for div in div_list:
# xpath返回的是列表，但是列表元素一定是Selector类型的对象
# extract可以将Selector对象中存储在data中的字符串提取出来
# author = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
author = div.xpath(
'./div[1]/a[2]/h2/text() | ./div[1]/span/h2/text()'
).extract_first().strip()
content = div.xpath('./a/div/span[1]//text()').extract()
content = ''.join(content)
content = content.strip()
item = QiubaiproItem()
item['author'] = author
item['content'] = content
yield item
def parse(self, response):
# 推荐xpath(scrapy里集成了xpath解析接口)
# 每个段子的外层容器
div_list = response.xpath('//div[@id="content-left"]/div')
for div in div_list:
author = div.xpath('./div/a[2]/h2/text()').extract_first()
content = div.xpath('.//div[@class="content"]/span/text()').extract_first()
# step001 将解析到的数据 存到items对象
item = QiubaiproItem()
item['author'] = author
item['content'] = content
# step002 将item对象提交给管道
yield item
def parse(self, response):
# 解析：作者的名称 + 段子内容
div_list = response.xpath('//div[@class="col1 old-style-col1"]/div')
all_data = [] # 存储所有解析到的数据
for div in div_list:
# xpath返回的是列表，但是列表元素一定是Selector类型的对象
# extract()可以将Selector对象中data参数存储的字符串提取出来
# author_name = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
author = div.xpath('./div[1]/a[2]/h2/text() | ./div[1]/span[2]/h2/text()').extract_first() # 如果列表中只有一个元素可以用该方法
# 如果列表调用了extract之后，则表示将列表中每一个Selector对象data对应的字符串提取出来
content = div.xpath('./a[1]/div/span//text()').extract()
content = ''.join(content)
item = QiubaiproItem()
item['author'] = author
item['content'] = content
yield item # 将item提交给了管道
def parse(self, response):
# 解析作者的名称+段子内容
div_list = response.xpath('//div[@id="content-left"]/div')
all_data = []
for div in div_list:
# 返回为列表，列表元素为selector类型的对象
# extract可以将selector对象中data参数存储字符串提取出来
author = div.xpath(
'./div[1]/a[2]/h2/text() | ./div[1]/span/h2/text()'
).extract_first()
content = div.xpath('./a[1]/div/span//text()').extract()
content = ''.join(content)
item = QiubaiproItem()
item['author'] = author
item['content'] = content
# 将item提交给管道
yield item
def parse(self, response):
# 解析：作者名称 + 段子内容、
div_list = response.xpath('//*[@id="content"]/div/div[2]/div')
all_data = [] # 存储所有解析到的数据
for div in div_list:
# xpath返回的是列表，但是列表元素一定是Selector类型的对象
# extract可以将Selector对象中data参数存储的字符串提取出来
# author = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
author = div.xpath('./div[1]/a[2]/h2/text()').extract_first()
# 列表调用了extract之后，则表示将列表中每一个Selector对象中data对应的字符串提取了出来
content = div.xpath('./a[1]/div/span//text()').extract()
content = ''.join(content)
item = QiubaiproItem()
item['author'] = author
item['content'] = content
yield item # 将item提交给管道
def parse(self, response):
#解析作者的名称和段子的内容（全部）
div_list = response.xpath('//div[@class="col1 old-style-col1"]/div')
for div in div_list:
# extract() 可以将selector 中参数data存储的字符串提取出来
# author = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
author = div.xpath(
'./div[1]/a[2]/h2/text() | ./div[1]/span/h2/text()'
).extract_first()
# 列表调用 extract()之后，表示将selector中的每一个data中的字符串提取出来
text = div.xpath('./a[1]/div/span//text()').extract()
text = "".join(text) #将列表转为字符串
item = QiubaiproItem() #实例化一个item对象
#封装到item中
item['author'] = author
item['text'] = text
yield item #将item提交给管道
def parse(self, response):
# 解析：作者的名称+段子的内容
div_list = response.xpath('//*[@id="content"]/div/div[2]/div')
# print(div_list)
for div in div_list:
# xpath返回的是列表，但是列表元素一定是Selector类型的对象
# extract可以将Selector对象中data参数存储的字符串提取出来
author = div.xpath('./div[1]/a[2]/h2/text()').extract_first()
# 列表调用了extract之后，则表示将列表中每一个Selector对象中data对应的字符串提取出来
content1 = div.xpath('./a[1]/div/span/text()').extract()
# 将content中的元素连接成一个字符串
content2 = ''.join(content1)
#将解析的数据封装存储到item类型的对象中
item = QiubaiproItem()
item['author'] = author
item['content'] = content2
#将item类型的对象提交给管道进行持久化存储的操作
yield item
def parse(self, response):
div_list = response.xpath('//div[@class="col1 old-style-col1"]/div')
all_data = []
for div in div_list:
#extract()方法提取selector对象的数据
author = div.xpath('./div[1]/a[2]/h2/text()').extract_first()
if author == None:
author = "匿名用户"
content = div.xpath('./a[1]/div/span[1]//text()').extract()
content = ''.join(content)
item = QiubaiproItem()
#item.Field()方法基本上继承了字典，所以用字典的访问方式
item['author'] = author
item['content'] = content
yield item
if self.page_num <= 11:
new_url = self.url + str(self.page_num)
self.page_num += 1
#手动请求发送：callback回调函数是专门用于作数据解析
yield scrapy.Request(url=new_url, callback=self.parse)
def parse(self, response):
divs = response.xpath(
'//div[contains(@class,"col1 old-style-col1")]/div')
for div in divs:
author = div.xpath(
'./div[1]/a[2]/h2/text() | ./div[1]/span[2]/h2/text()')[0]
content = div.xpath('./a[1]/div/span//text()') # 有其他子标签用//text()!!
# extract or extract_first
#print(author.extract().strip()) # 将selector中的data对象提取
#print("".join(content.extract()).replace(" ","").strip())
#print('======')
##############################
# 基于管道, 指令的方式见资料代码
##############################
item = QiubaiproItem()
item['author'] = author.extract().strip()
item['content'] = "".join(content.extract()).replace(" ",
"").strip()
yield item
def parse(self, response):
div_list = response.xpath('//div[@id="content-left"]/div')
for div in div_list:
#数据指纹：爬取到一条数据的唯一标识
author = div.xpath('./div/a[2]/h2/text() | ./div/span[2]/h2/text()'
).extract_first()
content = div.xpath('./a/div/span//text()').extract()
content = ''.join(content)
item = QiubaiproItem()
item['author'] = author
item['content'] = content
#数据指纹的创建
data = author + content
hash_key = hashlib.sha256(data.encode()).hexdigest()
ex = self.conn.sadd('hash_keys', hash_key)
if ex == 1:
print('有新数据更新......')
yield item
else:
print('无数据更新！')
def parse(self, response):
content = response.xpath('//div[@id="content"]')
content_left = content.xpath('./div[1]/div[2]')
div_list = content_left.xpath('./div')
# 解析作者名称 段子内容
for div in div_list:
# xpath返回的是列表，但元素一定是selector类型
# extract可以将select对象中data提取
# author = div.xpath('./div[1]/a[2]/h2/text()').extract_first()
author = div.xpath(
'./div[1]/a[2]/h2/text() | ./div[1]/span/h2/text()'
)[0].extract()
# content = div.xpath('./a[1]/div/span//text()')[0].extract()
# 将每一个列表元素的data提取
content = div.xpath('./a[1]/div/span//text()').extract()
content = ''.join(content)
item = QiubaiproItem()
item['author'] = author
item['content'] = content
yield item
def parse(self, response):
# 解析：作者名称和段子的内容
div_list = response.xpath(
'//*[@class="content-block clearfix"]/div[2]/div')
for div in div_list:
# xpath返回的是列表，但是列表元素一定是selector类型对象
# extract()可以将selector对象中data参数存储的字符串提取出来
author = div.xpath('./div[1]/a[2]/h2/text()').extract()
author = ''.join(author)
#author = author.strip('\n')
# 列表调用了.extract()之后，则表示将列表中每一个selector对象中data对应的字符串提取出来
content = div.xpath(
'./a[1]/div/span//text()|./div[1]/span/h2/text()').extract()
#content = content.strip('\n')
content = ''.join(content)
item = QiubaiproItem()
item['author'] = author
item['content'] = content
# 将item提交给pipeline
yield item
