#!/usr/bin/env python
# -*- coding: utf-8 -*-
from codecs import getwriter
from linklist import parse_linklist, serialize_webvtt
from sys import argv, stdin, stdout
stdout = getwriter("utf-8")(stdout)
data = parse_linklist(stdin.read(), remove_tags=True)
data = filter(lambda e: e["url"] == "", data)
last_chapter_end = argv[1]
stdout.write(serialize_webvtt(data, last_chapter_end))
url = element['url']
if url == '':
continue
scheme = urlparse.urlsplit(url).scheme
host = urlparse.urlsplit(url).netloc
if scheme in ('http', 'https') and \
url_status_cache.get(url) is not True:
try:
request = head(url, timeout=10)
# some web sites cannot into head requests
if request.status_code in (403, 405, 500) or \
host in ('mobil.morgenpost.de'):
request = get(url)
except Timeout as e:
stderr.write('Connection to <%s> timeouted.\n' % url)
exit(1)
except ConnectionError as e:
stderr.write('Connection to <%s> failed.\n' % url)
stderr.write(str(e) + '\n')
exit(1)
if request.ok:
url_status_cache.set(url, request.ok)
else:
stderr.write('<%s> is unreachable.\n' % url)
exit(1)
pbar.update(i + 1)
data = parse_linklist(stdin.read())
validate_links(data)
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from codecs import getwriter
from linklist import parse_linklist, serialize_webvtt
from sys import argv, stdin, stdout
stdout = getwriter('utf-8')(stdout)
data = parse_linklist(stdin.read(), remove_tags=True)
data = filter(lambda e: e['url'] == '', data)
last_chapter_end = argv[1]
stdout.write(serialize_webvtt(data, last_chapter_end))
#!/usr/bin/env python # -*- coding: utf-8 -*- from linklist import parse_linklist, serialize_html_table from sys import stdin, stdout data = parse_linklist(stdin.read()) data = filter(lambda e: e['url'] != '', data) stdout.write(serialize_html_table(data))