Python 之lxml解析庫

一、xpath常用規則

二、解析html檔案

from lxml import

etree
#讀取html檔案進行解析
defparse_html_file():
html = etree.parse("
./test.html
", parser=etree.htmlparser())
print(etree.tostring(html).decode("
utf-8"))
'''    
'''#
讀取文字解析節點
defget_text_node(text):
html = etree.html(text, parser=etree.htmlparser())
print(html.xpath("
//ul/li[position()=2]/text()
"))  #
['你好！！！']
print(html.xpath("
//ul/li[2]/text()
"))  #
['你好！！！']
#獲取所有節點
defget_all_node(text):
html = etree.html(text, parser=etree.htmlparser())
print
(html.xpath(
"//*
"))  #
[, , , , , , , , ]
#獲取子節點
defget_children_node(text):
html = etree.html(text, parser=etree.htmlparser())
print(html.xpath("
//div/ul/li/a
"))  #
#獲取父節點
defget_parent_node(text):
html = etree.html(text, parser=etree.htmlparser())
print(html.xpath("
//a/..
"))  #
[, ]
#屬性匹配
defmath_attr(text):
html = etree.html(text, parser=etree.htmlparser())
print(html.xpath("
//a[@href='2.html']/text()
"))  #
['hello world']
#屬性獲取
defget_attr(text):
html = etree.html(text, parser=etree.htmlparser())
print(html.xpath("
//a/@href
"))  #
['1.html', '2.html']
#屬性多值匹配
defmatch_more_attr(text):
html = etree.html(text, parser=etree.htmlparser())
print(html.xpath("
//li[contains(@class, 'aaa')]/a/text()
"))  #
['yangs']
if__name__ == '
__main__':
text = '''
'''

import

requests
from lxml import
etree
defgo_where(keyword):
url = "
" +keyword
headers =
try:
html = requests.get(url, headers=headers).content.decode("
utf-8")
except
runtimeerror as e:
print
(e)    
try:
html_object = etree.html(html, parser=etree.htmlparser())
#獲取總共多少條資料
count = len(html_object.xpath("
//div[@class='sight_item']"))
return_data =
for i in
range(count):
name = html_object.xpath("
//div[@class='sight_item']/@data-sight-name")
districts = html_object.xpath("
//div[@class='sight_item']/@data-districts")
point = html_object.xpath("
//div[@class='sight_item']/@data-point")
img_url = html_object.xpath("
//div[@class='sight_item']/@data-sight-img-u-r-l")
address = html_object.xpath("
//div[@class='sight_item']/@data-address")
"name
": name[i],
"districts
": districts[i],
"point
": point[i],
"address
": address[i],
"img_url
": img_url[i]
})return
return_data
except
runtimeerror as e:
print
(e)if
__name__ == '
__main__':
data = go_where("溫州"
)    
print(data)  #
[, , , , , , , , , , ]

Python 之lxml解析模組

lxml 是 乙個html xml的解析器，主要的功能是如何解析和提取 html xml 資料。一 lxml示例 1 初步 使用 lxml 的 etree 庫 from lxml import etree text 利用etree.html，將字串解析為html文件 html etree.html ...

python的lxml庫簡介 lxml庫

lxml 是 乙個html xml的解析器，主要的功能是如何解析和提取 html xml 資料。lxml和正則一樣，也是用 c 實現的，是一款高效能的 python html xml 解析器，我們可以利用之前學習的xpath語法，來快速的定位特定元素以及節點資訊。需要安裝c語言庫，可使用 pip 安...

python爬蟲網頁解析之lxml模組

windows系統下的安裝 方法一 pip3 install lxml pip3 install lxml 4.2.1 cp36 cp36m win amd64.whl 檔案所在的路徑 linux下安裝 方法一 pip3 install lxml 方法二 yum install y epel rel...