Heim >Backend-Entwicklung >PHP-Tutorial >爬虫如何获得biilbili播放数?
<i id="dianji" title="播放"></i><i id="dm_count" title="弹幕"></i><i id="stow_count" title="收藏"></i><i id="pt"><span class="v_ctimes" title="硬币数量"></span></i>
<code class="language-python"><span class="c"># encoding=utf8</span>
<span class="c"># author:shell-von</span>
<span class="kn">import</span> <span class="nn">requests</span>
<span class="kn">import</span> <span class="nn">re</span>
<span class="n">aid</span> <span class="o">=</span> <span class="s">'3210612'</span>
<span class="n">api_key</span> <span class="o">=</span> <span class="s">"http://interface.bilibili.com/count?key=27f582250563d5d6b11d6833&aid=</span><span class="si">%s</span><span class="s">"</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">requests</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">api_key</span> <span class="o">%</span> <span class="n">aid</span><span class="p">)</span><span class="o">.</span><span class="n">content</span>
<span class="n">regex</span> <span class="o">=</span> <span class="s">r"\('(?:.|#)([\w_]+)'\)\.html\('?(\d+)'?\)"</span>
<span class="k">print</span> <span class="nb">dict</span><span class="p">(</span><span class="n">re</span><span class="o">.</span><span class="n">findall</span><span class="p">(</span><span class="n">regex</span><span class="p">,</span> <span class="n">data</span><span class="p">))</span>
</code>
以前写过一个。。。。<code class="language-matlab"><span class="n">aid</span> <span class="p">=</span> <span class="mi">3295561</span><span class="p">;</span>
<span class="n">api</span> <span class="p">=</span> <span class="s">'http://interface.bilibili.com/count?key=b9415053057bb00966665eaa'</span><span class="p">;</span>
<span class="n">data</span> <span class="p">=</span> <span class="n">regexp</span><span class="p">(</span><span class="n">webread</span><span class="p">(</span><span class="n">api</span><span class="p">,</span><span class="s">'aid'</span><span class="p">,</span><span class="n">aid</span><span class="p">),</span><span class="s">'#(\w)+\D*(\d)+'</span><span class="p">,</span><span class="s">'tokens'</span><span class="p">);</span>
<span class="n">data</span> <span class="p">=</span> <span class="p">[</span><span class="n">data</span><span class="p">{:}]</span>
</code>
说下大概的思路。<code class="language-text">import urllib2
import re
from StringIO import StringIO
import gzip
def find_cid_aid(html):
target = re.compile('EmbedPlayer(?P<args>.*?)',re.DOTALL)
cidaid = target.search(html)
cidaid = html[cidaid.start('args'):cidaid.end('args')]
cid = cidaid.find('cid=')
aid = cidaid.find('&aid=')
index = aid
while cidaid[index] != '"':
index += 1
return (cidaid[cid + 4:aid],cidaid[aid + 5:index])
def find_how_many(cid_aid):
target = re.compile(r'<click>(?P<result>.*?)</result></click>',re.DOTALL)
cid = cid_aid[0]
aid = cid_aid[1]
addr = r'http://interface.bilibili.com/player?id=cid:' + cid + '&aid=' + aid
f = urllib2.urlopen(addr)
res = f.read()
target = target.search(res)
return res[target.start('result'):target.end('result')]
headers = {'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', \
'Accept-Language':'zh-cn,zh;q=0.8,en-us;q=0.5,en;q=0.3', \
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; rv:28.0) Gecko/20100101 Firefox/28.0',\
'Host':'www.bilibili.com', \
'Accept-Encoding':'gzip, deflate', \
'Cache-Control':'max-age=0', \
'Connection':'keep-alive'}
request = urllib2.Request(r'http://www.bilibili.com/video/av2046145/', headers=headers)
html = urllib2.urlopen(request)
if html.info().get('Content-Encoding') == 'gzip':
buf = StringIO(html.read())
f = gzip.GzipFile(fileobj=buf)
html = f.read()
cid_aid = find_cid_aid(html)
print find_how_many(cid_aid)
</args></code>
获取cid aid请求http://interface.bilibili.com/playercid=1511100&aid=1044050
http://interface.bilibili.com/player?id=cid:1511100&aid=1044050
<code class="language-text"><click>4611</click>
</code>
你在电脑屏幕上面看到的一切都是数据来着啊。B站的网页也只不过是一堆代码而已。稍微获取一下源代码,解gzip压缩,转换一下编码,正则表达式搜索一下,就能出来了,很简单的。