css选择器简单使用

2019-01-28  本文已影响0人  徒手說梦话
from bs4 import BeautifulSoup

html = """
    <table class="tablelist" cellpadding="0" cellspacing="0">
                <tbody><tr class="h">
                    <td class="l" width="374">职位名称</td>
                    <td>职位类别</td>
                    <td>人数</td>
                    <td>地点</td>
                    <td>发布时间</td>
                </tr>
                                <tr class="even">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47342&amp;keywords=python&amp;tid=0&amp;lid=0">TEG05-高级安全策略工程师(深圳)</a></td>
                    <td>技术类</td>
                    <td>1</td>
                    <td>深圳</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="odd">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47331&amp;keywords=python&amp;tid=0&amp;lid=0">18428-财付通平台组件测试工程师</a></td>
                    <td>技术类</td>
                    <td>1</td>
                    <td>深圳</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="even">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47318&amp;keywords=python&amp;tid=0&amp;lid=0">CSIG07-基础安全威胁情报分析师</a></td>
                    <td>技术类</td>
                    <td>4</td>
                    <td>深圳</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="odd">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47319&amp;keywords=python&amp;tid=0&amp;lid=0">CSIG07-业务威胁情报分析师</a></td>
                    <td>技术类</td>
                    <td>1</td>
                    <td>深圳</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="even">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47320&amp;keywords=python&amp;tid=0&amp;lid=0">CSIG07-业务威胁情报分析师</a></td>
                    <td>技术类</td>
                    <td>2</td>
                    <td>深圳</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="odd">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47317&amp;keywords=python&amp;tid=0&amp;lid=0">25925-数据挖掘工程师</a></td>
                    <td>技术类</td>
                    <td>2</td>
                    <td>深圳</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="even">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47311&amp;keywords=python&amp;tid=0&amp;lid=0">PCG04-测试开发高级工程师(深圳)</a></td>
                    <td>技术类</td>
                    <td>1</td>
                    <td>深圳</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="odd">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47297&amp;keywords=python&amp;tid=0&amp;lid=0">28603-116 微信支付效能开发工程师(深圳)</a></td>
                    <td>技术类</td>
                    <td>1</td>
                    <td>深圳</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="even">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47299&amp;keywords=python&amp;tid=0&amp;lid=0">28601-微信支付行业缴费开发工程师(深圳)</a></td>
                    <td>技术类</td>
                    <td>1</td>
                    <td>深圳</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="odd">
                    <td class="l square"><a target="_blank" href="position_detail.php?id=47300&amp;keywords=python&amp;tid=0&amp;lid=0">19157-车联物联安全—固件/硬件安全研究员(上海)</a></td>
                    <td>技术类</td>
                    <td>1</td>
                    <td>上海</td>
                    <td>2019-01-27</td>
                </tr>
                                <tr class="f">
                    <td colspan="5">
                        <div class="left">共<span class="lightblue total">550</span>个职位</div>
                        <div class="right"><div class="pagenav"><a href="javascript:;" class="noactive" id="prev">上一页</a><a class="active" href="javascript:;">1</a><a href="position.php?keywords=python&amp;start=10#a">2</a><a href="position.php?keywords=python&amp;start=20#a">3</a><a href="position.php?keywords=python&amp;start=30#a">4</a><a href="position.php?keywords=python&amp;start=40#a">5</a><a href="position.php?keywords=python&amp;start=50#a">6</a><a href="position.php?keywords=python&amp;start=60#a">7</a><a href="position.php?keywords=python&amp;start=70#a">...</a><a href="position.php?keywords=python&amp;start=540#a">55</a><a href="position.php?keywords=python&amp;start=10#a" id="next">下一页</a><div class="clr"></div></div></div>
                        <div class="clr"></div>
                    </td>
                </tr>
            </tbody></table>
"""

soup = BeautifulSoup(html,'lxml')

# 获取所以的tr标签
# trs = soup.select("tr")

# 获取第二个tr标签
""" 
tr = soup.select("tr")[1]
print(tr) 
"""

# 获取所以class等于even的tr标签
# trs = soup.select("tr.even")

# 获取所以a标签的href属性
""" 
trs = soup.select("a")
for a in trs:
    href = a['href'] 
"""

# 获取所有职位信息
trs = soup.select('tr')[:-1]
for tr in trs:
    infos = list(tr.stripped_strings)
上一篇 下一篇

猜你喜欢

热点阅读