def parse(self, response):
contentLeft = response.xpath(
"//div[@id='content-left']/div"
) # 获得的数据是 SelectorList 类型，实际上也是继承 Selector
# items = []
for duanzidiv in contentLeft:
# print(duanzidiv)
author = duanzidiv.xpath(".//h2/text()").get().strip()
content = duanzidiv.xpath(
".//div[@class='content']//text()").getall()
content = "".join(content).strip()
# duanzi = {'author':author, 'content':content}
item = QsbkItem(author=author, content=content) # 不使用字典返回，返回item
yield item
# items.append(item)
# return items
next_url = response.xpath(
"//ul[@class='pagination']/li[last()]/a/@href").get()
print('网页' + next_url)
print("=" * 50)
if not next_url:
return
else:
# 发送另外一个请求 callback 代表请求回来后，执行self.parse()的函数
yield scrapy.Request(self.base_domain + next_url,
callback=self.parse)
def parse(self, response):
# 返回结果为SelectorList
duanzidivs = response.xpath("//div[@id='content-left']/div")
items = []
for duanzidiv in duanzidivs:
# 循环每一个Selector,调用get()返回unicode字符串
author = duanzidiv.xpath(".//h2/text()").get().strip()
# 获取所有内容getall,返回一个列表
content = duanzidiv.xpath(
".//div[@class='content']//text()").getall()
# "".join把列表转换为字符串
content = "".join(content).strip()
# 约束我们传递的参数数量
item = QsbkItem(author=author, content=content)
# 第一种方式：转换为生成器
yield item
# 第二种方式定义列表，return列表
# items.append(item)
# return items
next_url = response.xpath(
"//ul[@class='pagination']/li[last()]/a/@href").get()
if not next_url:
return
else:
# 携带当前参数(下一页的url)，回调当前请求并再次解析
yield scrapy.Request(self.base_domain + next_url,
callback=self.parse)
def parse(self, response):
content_letf = response.xpath('//div[@id="content-left"]/div')
for duanzidiv in content_letf:
# 判断是否存在“阅读全文”按钮
content_for_all = duanzidiv.xpath(
'.//span[@class="contentForAll"]')
if content_for_all:
content_url = duanzidiv.xpath(
'.//a[@class="contentHerf"]/@href').get()
# 请求详情页，获得完整的段子
yield scrapy.Request(self.base_domain + content_url,
callback=self.parse_content)
continue
# 作者
author = duanzidiv.xpath('.//h2/text()').get().strip()
# 好笑值
stats_vote = duanzidiv.xpath(
'.//span[@class="stats-vote"]/i/text()').get()
# 内容
contents = duanzidiv.xpath(
'.//div[@class="content"]//span/text()').getall()
content = "".join(contents).strip().replace('\"', ' ')
item = QsbkItem(author=author,
stats_vote=stats_vote,
content=content)
yield item
next_url = response.xpath(
'//ul[@class="pagination"]/li[last()]/a/@href').get()
if not next_url:
return
else:
# 请求下一页
yield scrapy.Request(self.base_domain + next_url,
callback=self.parse)
def parse(self, response):
"""
提取数据
:param response: 下载完成数据；类型为HtmlResponse
"""
# response.xpath() 提取出来的数据类型为SelectorList
liList = response.xpath('//div[@class="j-r-list"]/ul/li')
for li in liList:
# Selector: get()将Selector转换为uncode
author = li.xpath('.//div[@class="u-txt"]/a/text()').get()
content = li.xpath(
'.//div[@class="j-r-list-c"]/div[@class="j-r-list-c-desc"]/a/text()'
).getall()
content = "".join(content).strip()
# 规范，固定传递指定参数
item = QsbkItem(author=author, content=content)
yield item # ==> itmes.append(item)
'''
爬取下一页：获取"下一页"的链接，再次回调parse方法。直到无"下一页"链接则return方法
'''
next_url = response.xpath(
'//div[@class="j-page"]//a[@class="pagenxt"]/@href').get()
if not next_url:
return
elif int(next_url) == 51:
# 51页无数据
print("最后一页啦 %s" % next_url)
return
else:
# 返回当前请求给parse()；不能用return（会停止执行parse方法）
yield scrapy.Request(self.base_domains + next_url,
callback=self.parse)
def parse(self, response):
base_url = "https://www.qiushibaike.com"
# SelectorList
duanziDivs = response.xpath("//div[@id='content-left']/div")
# 遍历SelectorList得到Selector
for duanziDiv in duanziDivs:
# extract()得到符合条件的所有元素提取html代码,等价于getall(),返回列表
# extract_first()得到符合条件的第一个元素并提取其html代码,等价于get()
author = duanziDiv.xpath(".//h2/text()").get().strip()
content = duanziDiv.xpath(
".//div[@class='content']//text()").getall()
content = "".join(content).strip()
item = QsbkItem(author=author, content=content)
yield item
next_url = response.xpath(
"//ul[@class='pagination']/li[last()]/a/@href").get()
if not next_url:
return
else:
next_url = base_url + next_url
yield scrapy.Request(next_url, callback=self.parse)
def parse(self, response):
duanzidivs = response.xpath('//div[@id="content-left"]/div')
for duanzi in duanzidivs:
author = duanzi.xpath(".//h2/text()").get().strip()
content = duanzi.xpath(".//div[@class='content']//text()").getall()
content = "".join(content).strip()
item = QsbkItem(author=author, content=content)
yield item
def parse(self, response):
i = QsbkItem()
i['content'] = response.xpath(
'//div[@class="content"]/span/text()').extract()
# i['link'] = response.xpath('//div[@id="qiushi_tag_120320318"]/@href').extract()
# i['data'] = response.xpath('//i[@class="number"]').extract()
print(i['content'])
return i
def parse(self, response):
coon = response.xpath('//div[@id="footzoon"]')
contents = coon.xpath('.//div[@id="endtext"]/text()').getall()
for content in contents:
content = content.strip()
item = QsbkItem(content=content)
print(content)
yield item
def parse_item(self, response):
i = QsbkItem()
selector=Selector(response)
i['content'] = selector.xpath('//*[@id="single-next-link"]/div/text()').extract()
# i['link'] = response.xpath('//div[@id="qiushi_tag_120320318"]/@href').extract()
# i['data'] = response.xpath('//i[@class="number"]').extract()
print(i['content'])
return i
time.sleep(10)
def parse(self, response):
print('*' * 40)
# node_list = response.xpath("//div[@id='big_pic']")
node_list = response.xpath("//a[@href='/weimei/48095.html']")
for node in node_list:
item = QsbkItem()
name = node.xpath("img/@src").extract()
item['url'] = name[0]
yield item
print('*' * 40)
def parse(self, response):
duanzidiv = response.xpath("//div[@id='content-left']/div")
for dz in duanzidiv:
author = dz.xpath(".//h2/text()").get().strip()
content = dz.xpath(".//div[@class='content']//text()").getall()
content = ''.join(content).strip()
# print(author)
# print(content)
# duanzi2_ = {'author': author, 'content': content}
item = QsbkItem(author=author, content=content) # 可以这样简化写
yield item # 将数据移交给 piplines
def parse_content(self, response):
author = response.xpath(
'.//div[@class="detail-col0"]/a/img/@alt').get()
stats_vote = response.xpath(
'.//span[@class="stats-vote"]/i/text()').get()
content_page = response.xpath('.//div[@class="col1 new-style-col1"]')
contents = content_page.xpath(
'.//div[@class="content"]/text()').getall()
content = "".join(contents).strip().replace('\"', ' ')
item = QsbkItem(author=author, stats_vote=stats_vote, content=content)
yield item
def parse(self, response):
duanzi_div = response.xpath('//div[@id="content-left"]/div')
for duanzi in duanzi_div:
author = duanzi.xpath('.//h2/text()').get().strip()
content = duanzi.xpath('.//div[@class="content"]//text()').getall()
content = ''.join(content).strip()
item = QsbkItem(author=author, content=content)
yield item
next_url = response.xpath(
'//ul[@class="pagination"]/li[last()]/a/@href').get()
if next_url:
yield scrapy.Request(self.base_url + next_url, self.parse)
def parse(self, response):
duanzidiv = response.xpath("//div[@id = 'content-left']/div")
for duanzi in duanzidiv:
author = duanzi.xpath(".//h2/text()").get().strip()
content = duanzi.xpath(".//div[@class= 'content']//text()").getall()
content = ''.join(content)
item = QsbkItem(author=author, content=content)
yield item
next_url = response.xpath("//ul[@class =[pagination']/li[last()]/a/@href").get()
if not next_url:
return
else:
yield scrapy.Request(self.base_domain+next_url, callback=self.parse)
def parse(self, response):
duanzidivs = response.xpath('//div[@id="content-left"]/div')
for duanzidiv in duanzidivs:
author = duanzidiv.xpath(".//h2/text()").get().strip()
content = duanzidiv.xpath('.//div[@class="content"]//text()'
).getall() # extract = getall
content = ''.join(content).strip()
#方法一：以字典的方式传回，不好
# duanzi = {'author':author,'content':content}
# yield duanzi
#方法二：使用items
item = QsbkItem(author=author, content=content)
yield item
def parse2(self,response):
try:
text = json.loads(response.text[20:-1])
comment_lists = text['result']['cmntlist']
# print(comment_lists)
for comment in comment_lists:
item = QsbkItem()
item['mid'] = comment['mid']
item['content'] = comment['content']
item['nick'] = comment['nick']
# print(item)
yield item
except:
pass
def parse(self, response):
# SelectorList
# 解析页面
content_left = response.xpath('//div[@id="content-left"]/div')
# 提取数据
for dz_div in content_left:
# Selector
author = dz_div.xpath(".//h2/text()").get().strip()
content_tmp = dz_div.xpath(
".//div[@class='content']//text()").getall()
content = ''.join(content_tmp).strip()
item = QsbkItem(author=author, content=content)
# 使用yield返回给pipeline
yield item
def parse(self, response):
contents = response.xpath("//div[@class='content']")
for content in contents:
text = content.xpath("text()").get().strip()
if text != "":
item = QsbkItem(content=text)
yield item
print("page {} finished...".format(response.url))
page_next = response.xpath("//div[@class='pagebar']/a[text()='下一页']/@href").get()
if not page_next:
return
else:
page_next_url = self.url_head + page_next
yield scrapy.Request(page_next_url,callback=self.parse)
def parse(self, response):
# selectorList 类型
duanziDivs = response.xpath("//div[@class='col1 old-style-col1']/div")
i = 0
for div in duanziDivs:
# div: Selector类型
# div.xpath()：selectorList类型
author = div.xpath(".//h2/text()").get().strip()
# get()函数，取到第一个结果（str类型）, get()<=>extract_first()
# extract(): 提取所有结果组成列表，每个元素是str类型
# strip(): 去掉前后的空格
href = div.xpath('./a/@href').get() # 获取a标签内的href的属性值
url = urljoin(self.start_urls[0],href) # 跳转到详情页
content = div.xpath(".//div[@class='content']//text()").extract()
# html中该div下有span标签，span中才是内容，//text()直接提取该内容
content = ''.join(content).strip()
# tplt = "{0:{2}<20}\t{1:^50}"
# print(tplt.format(author,url,chr(12288)))
# print(content)
# print('=' * 100)
# duanzi = {'author':author,'content':content} # 即为一个个的存储项，item，写法如下 ⬇
item = QsbkItem(author=author, content=content)
i += 1
print('生成器调用：',i)
# yield duanzi
yield item
# 若不使用生成器，即注释上面的yield item，可使用以下方法
# items = []
# items.append(item)
# return items
# 返回所有的items=，在pipelines中也可以被解析
next_path = response.xpath("//ul[@class='pagination']/li[last()]/a/@href").get() # 底部显示页面的最后一个li标签，‘下一页’
if not next_path: # 如果没有下一页
return
else:
next_url = urljoin(self.start_urls[0], next_path)
yield scrapy.Request(next_url, callback=self.parse) # 利用当前页的url，执行上面的parse解析函数
def parse(self, response):
duanzidivs = response.xpath('//div[@class="col1 old-style-col1"]/div')
for duanzidiv in duanzidivs:
author = duanzidiv.xpath('.//h2/text()').get().strip()
content = duanzidiv.xpath(
'.//div[@class="content"]//text()').getall()
content = ''.join(content).strip()
item = QsbkItem(author=author, content=content)
yield item
nextUrl = duanzidiv.xpath(
'//ul[@class="pagination"]/li[last()]/a/@href').get()
if not nextUrl:
return
else:
yield scrapy.Request(self.baseDomain + nextUrl,
callback=self.parse)
def parse(self, response):
# SelectorList
duanzidivs = response.xpath("//div[@id = 'content-left']/div")
for duanzidiv in duanzidivs:
# Selector
author = duanzidiv.xpath(".//h2/text()").get().strip()
content = duanzidiv.xpath(".//span/text()").getall()
content = "".join(content).strip()
item = QsbkItem(author=author, content=content)
# duanzi = {"author":author,"content":content}
yield item
next_url = response.xpath("//ul[@class= 'pagination']/li[last()]/a/@href").get()
if not next_url:
return
else:
yield scrapy.Request(self.base_domin + next_url, callback=self.parse)
def parse(self, response):
duanzidivs = response.xpath('//div[@id="content-left"]/div') # SelectorList类型
for duanzidiv in duanzidivs:
# duanzidiv是Selector类型
author = duanzidiv.xpath(".//h2/text()").get().strip()
content = duanzidiv.xpath(".//div[@class='content']//text()").getall()
content = ''.join(content).strip()
# duanzi = {'author': author, 'content': content}
item = QsbkItem(author=author, content=content)
yield item
next_url = response.xpath("//ul[@class='pagination']/li[last()]/a/@href").get()
if not next_url:
return
else:
# yield scrapy.Request(self.base_domains+next_url, callback=self.parse)
yield response.follow(next_url, callback=self.parse)
def parse(self, response):
duanzidivs = response.xpath(".//div[@id='content-left']/div")
for duanzidiv in duanzidivs:
author = duanzidiv.xpath(".//h2//text()").get().strip()
content = duanzidiv.xpath(
".//div[@class='content']//text()").getall()
content = "".join(content).strip()
item = QsbkItem(author=author, content=content)
yield item
next_url = response.xpath(
'//*[@id="content-left"]/ul/li[last()]/a/@href').get()
if not next_url:
return
else:
yield scrapy.Request(self.base_domain + next_url,
callback=self.parse)
def parse(self, response):
# items = []
outerbox = response.xpath("//div[@id='content-left']/div")
for box in outerbox:
author = box.xpath(".//div[contains(@class,'author')]//h2/text()").extract_first().strip()
content = box.xpath(".//div[@class='content']/span/text()").extract_first().strip()
item = QsbkItem(author=author,content=content)
# item["author"] = author
# item["content"] = content
yield item
# items.append(item)
next_url=response.xpath("//ul[@class='pagination']/li[last()]/a/@href").get()
if not next_url:
return
else :
yield scrapy.Request('https://www.qiushibaike.com'+next_url,callback=self.parse)
#return items
def parse(self, response):
# 返回SelectorList
article_divs = response.xpath('//div[@id="content-left"]/div')
for article_div in article_divs:
# 每个article_div的数据类型是Selector
author = article_div.xpath(
'.//div[@class="author clearfix"]//h2/text()').get()
# 获取所有指定div下面的文本
content = article_div.xpath(
'.//div[@class="content"]//text()').getall()
# 把文本连起来(join)并去空格
content = "".join(content).strip()
# 使用items.py中定义的字段来接收
item = QsbkItem()
item['author'] = author
item['content'] = content
yield item
def parse(self, response):
descs = response.xpath("//div[@class='j-r-list-c-desc']")
for desc in descs:
jokes = desc.xpath(".//text()").getall()
joke = "\n".join(jokes).strip()
link = desc.xpath(".//a/@href").get()
links = str(self.base_domain + link)
# link = self.base_domain+links
item = QsbkItem(joke=joke, links=links)
yield item
next_url = response.xpath("//a[@class='pagenxt']/@href").get()
if not next_url:
return
else:
yield scrapy.Request(self.base_domain + "/text/" + next_url,
callback=self.parse)
def parse(self, response):
divs = response.xpath('//div[@id="content-left"]/div')
for div in divs:
author = div.xpath('.//h2/text()').get().strip()
content = div.xpath(
'.//div[@class="content"]/span/text()').getall()
content = "".join(content).strip()
item = QsbkItem(author=author, content=content)
yield item
href = response.xpath(
'//ul[@class="pagination"]/li[last()]/a/@href').get()
if not href:
return
else:
nex_url = self.domain_url + href
yield scrapy.Request(nex_url, callback=self.parse)
def parse(self, response):
duanziDivs = contentLeft = response.xpath("//div[@id='content-left']/div")
for duanzidiv in duanziDivs:
author = duanzidiv.xpath(".//h2/text()").get().strip()
content = duanzidiv.xpath(".//div[@class='content']//text()").getall()
content = "".join(content).strip()
# duanzi = {"author":author,"content":content}
# yield duanzi
item = QsbkItem(author=author,content=content)
yield item
next_url = response.xpath("//ul[@class='pagination']/li[last()]/a/@href").get()
if not next_url:
return
else:
yield scrapy.Request(self.base_domain + next_url, self.parse)
def parse(self, response):
duanzidivs = response.xpath(r"//div[@class='col1 old-style-col1']/div")
for duanzidiv in duanzidivs:
author = duanzidiv.xpath(r".//a[2]/h2/text()").get()
author = "".join(author).strip() #去掉空格
content = duanzidiv.xpath(
r".//div[@class='content']/span/text()").getall()
content = "".join(content).strip() #去掉空格
item = QsbkItem(author=author, content=content)
yield item
next_url = response.xpath(
r"//ul[@class='pagination']/li[last()]/a/@href").get()
if not next_url:
return
else:
yield scrapy.Request(self.base_domain + next_url,
callback=self.parse)
def parse(self, response):
contentDivs = response.xpath("//div[@id='j_p_postlist']/div")
for contentDiv in contentDivs:
author = contentDiv.xpath('.//li[@class="d_name"]/a/text()').get()
content = contentDiv.xpath('.//cc/div[2]/text()').get().strip()
# print(author, content)
# tieba = {'author': author, 'content' : content}
item = QsbkItem(author=author, content=content)
yield item
next_url = response.xpath(
'//ul[@class="l_posts_num"]/li/a[last()-1]/@href').get()
if not next_url:
return
else:
yield scrapy.Request(self.base_domain + next_url, self.parse)
