File: htmlparser.py

package info (click to toggle)
python-nvchecker 2.16-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 736 kB
  • sloc: python: 4,801; makefile: 25
file content (41 lines) | stat: -rw-r--r-- 1,215 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
# MIT licensed
# Copyright (c) 2020 Ypsilik <tt2laurent.maud@gmail.com>, et al.
# Copyright (c) 2013-2020 lilydjwg <lilydjwg@gmail.com>, et al.

from lxml import html, etree

from nvchecker.api import session, GetVersionError

async def get_version(name, conf, *, cache, **kwargs):
  key = tuple(sorted(conf.items()))
  return await cache.get(key, get_version_impl)

async def get_version_impl(info):
  conf = dict(info)

  encoding = conf.get('encoding')
  parser = html.HTMLParser(encoding=encoding)
  data = conf.get('post_data')
  if data is None:
    res = await session.get(conf['url'])
  else:
    res = await session.post(conf['url'], body = data, headers = {
        'Content-Type': conf.get('post_data_type', 'application/x-www-form-urlencoded')
      })
  doc = html.fromstring(res.body, base_url=conf['url'], parser=parser)

  try:
    els = doc.xpath(conf.get('xpath'))
  except ValueError:
    if not conf.get('missing_ok', False):
      raise GetVersionError('version string not found.')
  except etree.XPathEvalError as e:
    raise GetVersionError('bad xpath', exc_info=e)

  version = [
    str(el)
    if isinstance(el, str)
    else str(el.text_content())
    for el in els
  ]
  return version