爬虫基础 之BeautifulSoup（bs4）(中)

每天进步一点点，五年之后大不同 。

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>
"""

bs = BeautifulSoup(html,'html5lib')

#获取所有的tr标签
# trs = bs.find_all('tr')
# for tr in trs:
#     print(tr)

# 获取第三个tr标签
# tr = bs.find_all('tr')[2]   #下标从 0开始
# print(tr)

# 获取所有class为even的tr标签
#attribute 属性
# trs = bs.find_all('tr',attrs={'class':'even'})
# for tr in trs:
#     print(tr)

#获取所有id=test class 也等于test 的a标签
# aList = bs.find_all('a',id='test',class_='test')
# aList = bs.find_all('a',attrs={'class':'test',"id":"test"})
# for a in aList:
#     print(a)
# 获取所有a标签的href属性
# aList = bs.find_all('a')
# for a in aList:
#     # print(a['href'])
#     print(a.attrs['href'])

#获取所有的职位信息

trs = bs.find_all('tr')[1:]

ress = [] #存放最终的结果
for tr in trs:
    movie = {}
    tds = tr.find_all('td')
    title = tds[0].string
    category = tds[1].string
    nums = tds[2].string
    base = tds[3].string
    pubtime = tds[4].string

    # movie = {
    #     'title':title,
    #     'category':category,
    #     'nums':nums,
    #     'base':base,
    #     'pubtime':pubtime,
    # }
    # ress.append(movie)
    infos = list(tr.stripped_strings)
    movie['title']= infos[0]
    movie['category']= infos[1]
    movie['nums']= infos[2]
    movie['base']= infos[3]
    movie['pubtime']= infos[4]
    ress.append(movie)
print(ress)

万水千山总是情，点个关注行不行。
你的一个小小举动，将是我分享更多干货的动力。
我的博客都是上下具有连贯性的，只看一篇可能不太懂，需要多篇结合在一起才能真正看懂，我是学习python的小颜，希望大家点个关注，一起沟通学习哦。