如何在 Python 中解析 XML 和 RSS feeds

import xml.etree.ElementTree as ET
import requests

# URL of the RSS feed (from DataImpulse site)
FEED_URL = "https://dataimpulse.com/tutorials-category/web-scraping-seo/feed/"

# Download the XML data
response = requests.get(FEED_URL)
xml_data = response.content

# Parse the XML
root = ET.fromstring(xml_data)

# In RSS feeds, items are inside 
channel = root.find("channel")
items = channel.findall("item")

# Print titles and links of the items
for item in items:
   title = item.findtext("title")
   link = item.findtext("link")
   print(f"Title: {title}")
   print(f"Link: {link}\n")
      
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
      
Copy

import requests
from lxml import etree

# URL of the RSS feed
FEED_URL = "https://dataimpulse.com/tutorials-category/web-scraping-seo/feed/"

# Download the XML data
response = requests.get(FEED_URL)
xml_data = response.content

# Parse XML
root = etree.fromstring(xml_data)
items = root.xpath("//channel/item")

# Show list of titles with numbers
print("Available blog posts:\n")
for item in items:
   title = item.findtext("title")
   print(title)
      
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
      
Copy

import requests
from xml.dom import minidom

# URL of the RSS feed
FEED_URL = "https://dataimpulse.com/tutorials-category/web-scraping-seo/feed/"

# Download XML data
response = requests.get(FEED_URL)
xml_data = response.content

# Parse XML with minidom
doc = minidom.parseString(xml_data)

# Get all  elements
items = doc.getElementsByTagName("item")

print(f"Total articles found in feed: {len(items)}\n")

# Show titles with links
for i, item in enumerate(items, start=1):
   title = item.getElementsByTagName("title")[0].firstChild.nodeValue
   link = item.getElementsByTagName("link")[0].firstChild.nodeValue
   print(f"{i}. {title}")
   print(f"   Link: {link}\n")

# Show raw XML of the first  (just for demo)
print("First  as raw XML:\n")
print(items[0].toprettyxml())
      
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
      
Copy

import requests
import xml.sax

# Custom handler for SAX parsing
class RSSHandler(xml.sax.ContentHandler):
   def __init__(self):
       super().__init__()
       self.current_tag = ""
       self.in_item = False
       self.title = ""
       self.link = ""
       self.counter = 0

   def startElement(self, name, attrs):
       if name == "item":
           self.in_item = True
           self.title = ""
           self.link = ""
       self.current_tag = name

   def characters(self, content):
       if self.in_item:
           if self.current_tag == "title":
               self.title += content
           elif self.current_tag == "link":
               self.link += content

   def endElement(self, name):
       if name == "item":
           self.counter += 1
           print(f"{self.counter}. {self.title.strip()}")
           print(f"   Link: {self.link.strip()}\n")
           self.in_item = False
       self.current_tag = ""

# Download the XML feed
FEED_URL = "https://dataimpulse.com/tutorials-category/web-scraping-seo/feed/"
response = requests.get(FEED_URL)
xml_data = response.content

# Parse XML with SAX
print("Parsing RSS feed with SAX...\n")
handler = RSSHandler()
xml.sax.parseString(xml_data, handler)

print(f"Total items parsed: {handler.counter}")
      
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
      
Copy

import requests
import untangle
from io import BytesIO

# RSS feed from DataImpulse
FEED_URL = "https://dataimpulse.com/tutorials-category/web-scraping-seo/feed/"

# Download XML
resp = requests.get(FEED_URL)
resp.raise_for_status()
xml_bytes = resp.content

# Parse XML with untangle (use BytesIO for bytes input)
doc = untangle.parse(BytesIO(xml_bytes))

# Get all  elements
items = doc.rss.channel.item

print("Articles from DataImpulse RSS:\n")

# Print articles
for i, it in enumerate(items, start=1):
   title = it.title.cdata if hasattr(it, "title") else ""
   link = it.link.cdata if hasattr(it, "link") else ""
   desc = it.description.cdata if hasattr(it, "description") else ""
  
   print(f"{i}. {title}")
   print(f"   Link: {link}")
   if desc:
       print(f"   Description: {desc}")
   print()

      
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
        
      
Copy