1. 爬虫前奏
明确目的,例如,爬取直播网站“某猫”英雄联盟版块主播名字和人气。找到数据对应的网页,分析网页的结构找到数据所在标签位置。
2. 具体方法
模拟HTTP请求,向服务器发送请求,获取到服务器返回给我们的HTML,用正则表达式提取需要的数据。
3. 代码示例
完整代码如下,50行代码搞定python原生爬虫。
import re #正则表达式模块
from urllib import request #通过request对象获取html页面
class Spider():
url = 'https://www.panda.tv/cate/lol'
root_pattern = '<div class="video-info">([\s\S]*?)</div>' #()表示只提取定位标签中间内容
name_pattern = '</i>([\s\S]*?)</span>'
number_pattern = '<span class="video-number">([\s\S]*?)</span>'
def __fetch_content(self): #私有方法,获取html页面
r = request.urlopen(Spider.url) #在实例方法里读取类变量url
htmls = r.read() #字节码
htmls = str(htmls,encoding = 'utf-8') #将字节码转为字符串
print(htmls)
return htmls
def __analysis(self,htmls):#分析htmls文本,通过正则表达式提取html文本中的主播名和人气值
root_html = re.findall(Spider.root_pattern,htmls)
anchors = []
for html in root_html:
name = re.findall(Spider.name_pattern,html)
number = re.findall(Spider.number_pattern,html)
anchor = {
'name':name,'number':number}
anchors.append(anchor)
print(anchors)
return anchors
def __refine(self,anchors): #精炼数据,剔除文本中的空格和换行符等内容,规范成易读的数据
targets = []
for target_list in anchors:
name = target_list['name'][0].strip()
number = target_list['number'][0]
one_people = {
'name':name,'number':number}
targets.append(one_people)
print(targets);
return targets
def __sort(self,anchors): #对精炼后的数据按主播人气值进行排序
anchors = sorted(anchors,key = self.__sort_seed,reverse = True)
return anchors
def __sort_seed(self,anchor): #设置排序规则
r = re.findall('\d*',anchor['number'])
number = float(r[0])
if '万' in anchor['number']:
number *= 10000
return number
def __show(self,anchors): #展示最终爬取的数据
for rank in range(0,len(anchors)):
print('rank ' + str(rank+1)
+ ':' +anchors[rank]['name']
+ ' ' + anchors[rank]['number'])
def go(self): #公开方法,go方法是Spider的入口方法
htmls = self.__fetch_content()
anchors = self.__analysis(htmls)
anchors = self.__refine(anchors)
anchors = self.__sort(anchors)
self.__show(anchors)
spider = Spider()
spider.go()
以下是print()
到控制台的数据:
- print(htmls)
data-pdt-ele="1">
英雄联盟 </a>
</div>
</div>
</li>
<li class="video-list-item video-no-tag video-no-cate " data-pdt-block="sd1-109" data-id="26657">
<a target="_blank" href="26657" class="video-list-item-wrap" data-pdt-ele="0" data-id="26657" >
<div class="video-cover ">
<img class="video-img video-img-lazy" data-original="https://i.h2.pdim.gs/90/e9c7aaa62412bb248c6829b04c56a3c7/w338/h190.jpg" alt="【吸血鬼教学各种细节】">
<div class="video-overlay"></div>
<div class="video-play"></div>
<div class="lottery-icon-list">
</div>
</div>
<div class="video-info">
<span class="video-title" title="【吸血鬼教学各种细节】">【吸血鬼教学各种细节】</span>
<span class="video-nickname" title="有毒i吸血鬼">
<i class="icon-hostlevel icon-hostlevel-11" data-level="11"></i>
有毒i吸血鬼 </span>
<span class="video-number">851</span>
<span class="video-station-info">
<i class="video-station-num">18人</i>
</span>
</div>
</a>
<div class="video-label">
<div class="video-label-content">
<a class="video-label-item label-color-0" href="/cate/lol"data-pdt-ele="1">
英雄联盟 </a>
</div>
</div>
</li>
<li class="video-list-item video-no-tag video-no-cate " data-pdt-block="sd1-110" data-id="2276191">
<a target="_blank" href="2276191" class="video-list-item-wrap" data-pdt-ele="0" data-id="2276191" >
<div class="video-cover ">
<img class="video-img video-img-lazy" data-original="https://i.h2.pdim.gs/90/6f46def671c207a8e4750a3c2ad2d092/w338/h190.jpg" alt="求订阅,artifact还可以">
<div class="video-overlay"></div>
<div class="video-play"></div>
<div class="lottery-icon-list">
</div>
</div>
<div class="video-info">
<span class="video-title" title="求订阅,artifact还可以">求订阅,artifact还可以</span>
<span class="video-nickname" title="高调的火星人">
<i class="icon-hostlevel icon-hostlevel-0" data-level="0"></i>
高调的火星人 </span>
<span class="video-number">846</span>
<span class="video-station-info">
<i class="video-station-num">0人</i>
</span>
</div>
</a>
<div class="video-label">
<div class="video-label-content">
<a class="video-label-item label-color-0" href="/cate/lol"data-pdt-ele="1">
英雄联盟 </a>
</div>
</div>
</li>
<li class="video-list-item video-no-tag video-no-cate " data-pdt-block="sd1-111" data-id="1193989">
<a target="_blank" href="1193989" class="video-list-item-wrap" data-pdt-ele="0" data-id="1193989" >
<div class="video-cover ">
<img class="video-img video-img-lazy" data-original="https://i.h2.pdim.gs/90/fa49782338c10a678915ecfb07891119/w338/h190.jpg" alt="刀妹专场这个中单刀妹最无敌不接受反驳">
<div class="video-overlay"></div>
<div class="video-play"></div>
<div class="lottery-icon-list">
</div>
</div>
<div class="video-info">
<span class="video-title" title="刀妹专场这个中单刀妹最无敌不接受反驳">刀妹专场这个中单刀妹最无敌不接受反驳</span>
<span class="video-nickname" title="爱唱歌的小南丶">
<i class="icon-hostlevel icon-hostlevel-1" data-level="1"></i>
爱唱歌的小南丶 </span>
<span class="video-number">825</span>
<span class="video-station-info">
<i class="video-station-num">3人</i>
</span>
</div>
</a>
<div class="video-label">
<div class="video-label-content">
<a class="video-label-item label-color-0" href="/cate/lol"data-pdt-ele="1">
英雄联盟 </a>
</div>
</div>
</li>
<li class="video-list-item video-no-tag video-no-cate " data-pdt-block="sd1-112" data-id="796585">
<a target="_blank" href="796585" class="video-list-item-wrap" data-pdt-ele="0" data-id="796585" >
<div class="video-cover ">
<img class="video-img video-img-lazy" data-original="https://i.h2.pdim.gs/90/3ca5b2f3cbeb62b9a443fa73e4186d44/w338/h190.jpg" alt="青铜皇帝在线锤号!一礼炮=锤号➕房管">
<div class="video-overlay"></div>
<div class="video-play"></div>
<div class="lottery-icon-list">
</div>
</div>
<div class="video-info">
<span class="video-title" title="青铜皇帝在线锤号!一礼炮=锤号➕房管">青铜皇帝在线锤号!一礼炮=锤号➕房管</span>
<span class="video-nickname" title="熊猫尼古拉斯胖虎">
<i class="icon-hostlevel icon-hostlevel-7" data-level="7"></i>
熊猫尼古拉斯胖虎 </span>
<span class="video-number">820</span>
<span class="video-station-info">
<i class="video-station-num">12人</i>
</span>
</div>
</a>
<div class="video-label">
<div class="video-label-content">
<a class="video-label-item label-color-0" href="/cate/lol"data-pdt-ele="1">
英雄联盟 </a>
</div>
</div>
</li