====== XML ======
===== Utiliser ElementTree =====
* Doc : [[https://docs.python.org/3/library/xml.etree.elementtree.html]]
import xml.etree.ElementTree as ET
tree = ET.parse("yourXMLfile.xml")
root = tree.getroot()
for child in root:
print(child.tag, child.attrib)
print(root[0][1].text)
print(root.findall("myTag"))
print(root[0].find("myOtherTag"))
===== Utiliser la librairie lxml =====
* Tutorial **lxml** : [[https://lxml.de/tutorial.html]]
* Infos: [[https://python.doctor/page-xml-python-xpath]]
pip install lxml
===== Utiliser BeautifulSoup4 =====
pip install beautifulsoup4
from bs4 import BeautifulSoup
import requests
xmlDict = {}
r = requests.get("http://www.site.co.uk/sitemap.xml")
xml = r.text
soup = BeautifulSoup(xml)
sitemapTags = soup.find_all("sitemap")
print "The number of sitemaps are {0}".format(len(sitemapTags))
for sitemap in sitemapTags:
xmlDict[sitemap.findNext("loc").text] = sitemap.findNext("lastmod").text
print xmlDict