# -*- codeing = utf-8 -*-
# coding=gbk
# @Autor:ggui20
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=33824&keywords=python&tid=87&lid=2218">22989-金融云区块链高级研发工程师(深圳)</a></td>
<td>技术类</td>
<td>1</td>
<td>深圳</td>
<td>2017-11-25</td>
</tr>
<tr class="odd">
<td class="l square"><a target="_blank" href="position_detail.php?id=29938&keywords=python&tid=87&lid=2218">22989-金融云高级后台开发</a></td>
<td>技术类</td>
<td>2</td>
<td>深圳</td>
<td>2017-11-25</td>
</tr>
<tr class="even">
<td class="l square"><a target="_blank" href="position_detail.php?id=31236&keywords=python&tid=87&lid=2218">SNG16-腾讯音乐运营开发工程师(深圳)</a></td>
<td>技术类</td>
<td>2</td>
<td>深圳</td>
<td>2017-11-25</td>
</tr>
<tr class="odd">
<td class="l square"><a target="_blank" href="position_detail.php?id=31235&keywords=python&tid=87&lid=2218">SNG16-腾讯音乐业务运维工程师(深圳)</a></td>
<td>技术类</td>
<td>1</td>
<td>深圳</td>
<td>2017-11-25</td>
</tr>
<tr class="even">
<td class="l square"><a target="_blank" href="position_detail.php?id=34531&keywords=python&tid=87&lid=2218">TEG03-高级研发工程师(深圳)</a></td>
<td>技术类</td>
<td>1</td>
<td>深圳</td>
<td>2017-11-24</td>
</tr>
<tr class="odd">
<td class="l square"><a target="_blank" href="position_detail.php?id=34532&keywords=python&tid=87&lid=2218">TEG03-高级图像算法研发工程师(深圳)</a></td>
<td>技术类</td>
<td>1</td>
<td>深圳</td>
<td>2017-11-24</td>
</tr>
<tr class="even">
<td class="l square"><a target="_blank" href="position_detail.php?id=31648&keywords=python&tid=87&lid=2218">TEG11-高级AI开发工程师(深圳)</a></td>
<td>技术类</td>
<td>4</td>
<td>深圳</td>
<td>2017-11-24</td>
</tr>
<tr class="odd">
<td class="l square"><a target="_blank" href="position_detail.php?id=32218&keywords=python&tid=87&lid=2218">15851-后台开发工程师</a></td>
<td>技术类</td>
<td>1</td>
<td>深圳</td>
<td>2017-11-24</td>
</tr>
<tr class="even">
<td class="l square"><a target="_blank" href="position_detail.php?id=32217&keywords=python&tid=87&lid=2218">15851-后台开发工程师</a></td>
<td>技术类</td>
<td>1</td>
<td>深圳</td>
<td>2017-11-24</td>
</tr>
<tr class="odd">
<td class="l square"><a id="test" class="test" target='_blank' href="position_detail.php?id=34511&keywords=python&tid=87&lid=2218">SNG11-高级业务运维工程师(深圳)</a></td>
<td>技术类</td>
<td>1</td>
<td>深圳</td>
<td>2017-11-24</td>
</tr>
</tbody>
</table>
'''
soup = BeautifulSoup(html, 'lxml')
# 1. 获取所有tr标签
trs = soup.select('tr')
#print(trs)
# 2. 获取第2个tr标签
tr = soup.select('tr')[1]
#print(tr)
# 3. 获取所有class等于even的tr标签
#tr = soup.select('.even')
tr = soup.select('tr[class="even"]')
#print(tr)
# 4. 获取所有a标签的href属性
alist = soup.select('a')
for a in alist:
href = a['href']
#print(href)
# 5. 获取所有的职位信息(纯文本)
trs = soup.select('tr')
for tr in trs:
info = list(tr.stripped_strings)
print(info)
09-select方法练习题
最新推荐文章于 2024-09-01 11:41:29 发布