xml 讀取
阿新 • • 發佈:2019-01-05
ElementTree
from xml.etree import ElementTree as ET
# xml_file = r"D:\Deep_Learning_data\yolo\gen_data\test_xml\2007_000323.xml"
root = ET.parse(xml_file).getroot()
img_name = root.find("filename").text
lxml
from lxml import etree html = etree.HTML(open('web.html',encoding='utf-8').read()) # 容錯率高 ''' 選取節點 ''' # print(len(html.xpath('//div'))) # print(len(html.xpath('/html/body/div'))) # 從根節點開始查詢 # print(len(html.xpath('//div/a'))) # 從全文中開始查詢 # print(len(html.xpath('//div/a/..'))) # 查詢該節點的父節點 . 該節點自己 # print(html.xpath("//div[@class='left']/a")) # [@class='xxx'] 查詢屬性