XPath语法和lxml模块（下）

1.解析字符串：

#解析字符串
from lxml import etree


text = """
<ul>
    <li><a href="#">a</a></li>
    <li><a href="#">a</a></li>
    <li><a href="#">a</a></li>
    <li><a href="#">a</a></li>
    <li><a href="#">a</a></li>
</ul>
"""

htmlElement = etree.HTML(text) #用etree.HTML(text)去解析html
print(etree.tostring(htmlElement,encoding='utf-8').decode('utf-8'))

2.解析html文档：

#解析html文档

from lxml import etree


# htmlElement = etree.parse('tencent.html')
#
# print(etree.tostring(htmlElement,encoding='utf-8').decode('utf-8'))
#拉钩html代码不规范所以 etree.parse方法解析失败  这时候我们需要 自己从创建htmk解析器

paser = etree.HTMLParser(encoding='utf-8')
htmlElement = etree.parse('lagou.html',parser=paser)
print(etree.tostring(htmlElement,encoding='utf-8').decode('utf-8'))

3.获取标签及相关信息：

from lxml import etree


paser = etree.HTMLParser(encoding='utf-8')
html = etree.parse('tencent.html',parser=paser)
# print(html)

# 获取所有的tr标签
# trs = html.xpath("//tr") #返回的是一个列表
#
# for tr in trs:
#     print(etree.tostring(tr,encoding='utf-8').decode('utf-8')) #序列化成字符串
#

# 获取第二个tr标签
# trs = html.xpath("//tr[2]") #返回的是一个列表
tr = html.xpath("//tr[2]")[0] #返回的是一个列表
print(etree.tostring(tr,encoding='utf-8').decode('utf-8'))

# 获取所有class 为even的 tr标签
# trs = html.xpath("//a[@target='_blank']")
trs = html.xpath("//tr[@class='even']")
for tr in trs:
    print(etree.tostring(tr,encoding='utf-8').decode('utf-8')) #序列化成字符串


# 获取所有 a标签的href属性
aList = html.xpath("//a/@href")
for a in aList:
    print("http://hr.tencent.com/"+a)


# 获取所有的职位信息
positions = []  #存放最终的结果
trs = html.xpath("//tr[position()>1]")
for tr in trs:
    href = tr.xpath(".//a/@href")[0]
    full_url = 'http://hr.tencent.com/'+href
    title = tr.xpath("./td[1]//text()")[0]
    category = tr.xpath("./td[2]//text()")[0]
    nums = tr.xpath("./td[3]//text()")[0]
    base = tr.xpath("./td[4]//text()")[0]
    pub_time = tr.xpath("./td[5]//text()")[0]

    position = {
        'title':title,
        'category':category,
        'nums':nums,
        'base':base,
        'pub_time':pub_time,
        'url':full_url,
    }

    positions.append(position)
print(positions)

以上的tencent.html文件里面内容如下：

<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&amp;keywords=python&amp;tid=87&amp;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&amp;keywords=python&amp;tid=87&amp;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&amp;keywords=python&amp;tid=87&amp;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&amp;keywords=python&amp;tid=87&amp;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&amp;keywords=python&amp;tid=87&amp;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&amp;keywords=python&amp;tid=87&amp;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&amp;keywords=python&amp;tid=87&amp;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&amp;keywords=python&amp;tid=87&amp;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&amp;keywords=python&amp;tid=87&amp;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 target="_blank" href="position_detail.php?id=34511&amp;keywords=python&amp;tid=87&amp;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>

此文件在pycharm里面创建即可。
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。