Das deutsche Python-Forum

Code: Alles auswählen

re.findall('<a .* href=".*"', source_code)

Code: Alles auswählen

re.findall(r'''a href="(.+?)">''', seiten_quelltext)

Code: Alles auswählen

import re, urllib.request
from urllib.parse import urljoin

b = "http://python-forum.de"
s = urllib.request.urlopen(b).read().decode('utf-8')

def get_a(b, s):
    for m in re.finditer(r"""(?is)<a[^>]*href[\s\n]*=[\s\n]*("[^"]*"|'[^']*')""", s):
        yield urljoin(b, m.group(1)[1:-1])

print(list(get_a(b, s)))

Code: Alles auswählen

import xml.parsers.expat

def start_element(name, attrs):
    if name == 'a':
        links.append(attrs['href'])

links = []
p = xml.parsers.expat.ParserCreate()
p.StartElementHandler = start_element

with open("irgendeine_datei.xml", "r") as f:
    p.Parse(f.read())

Code: Alles auswählen

#!/usr/bin/env python
# -*- coding: utf-8 -*-
from xml.etree import ElementTree as etree


def main():
    result = list()
    for _type, node in etree.iterparse('test.xml', ['start']):
        if node.tag == 'a':
            result.append(node.get('href'))
    print result


if __name__ == '__main__':
    main()

Code: Alles auswählen

import xml.etree.ElementTree

tree = xml.etree.ElementTree.parse("beispiel.xml")
links = tree.getiterator("a")
for link in links:
    print link.get("href")