#!/usr/bin/env python
# -*- coding: utf-8 -*-
+import datetime
+import email.utils
import errno
import gzip
import io
import json
import locale
import os
+import platform
import re
+import socket
import sys
import traceback
import zlib
-import email.utils
-import socket
-import datetime
try:
import urllib.request as compat_urllib_request
except ImportError: # Python 2
from urllib2 import HTTPError as compat_HTTPError
+try:
+ from urllib.request import urlretrieve as compat_urlretrieve
+except ImportError: # Python 2
+ from urllib import urlretrieve as compat_urlretrieve
+
+
try:
from subprocess import DEVNULL
compat_subprocess_get_DEVNULL = lambda: DEVNULL
def find_xpath_attr(node, xpath, key, val):
""" Find the xpath xpath[@key=val] """
assert re.match(r'^[a-zA-Z]+$', key)
- assert re.match(r'^[a-zA-Z@\s]*$', val)
+ assert re.match(r'^[a-zA-Z0-9@\s]*$', val)
expr = xpath + u"[@%s='%s']" % (key, val)
return node.find(expr)
else:
return (u'&%s;' % entity)
compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
-class AttrParser(compat_html_parser.HTMLParser):
+class BaseHTMLParser(compat_html_parser.HTMLParser):
+ def __init(self):
+ compat_html_parser.HTMLParser.__init__(self)
+ self.html = None
+
+ def loads(self, html):
+ self.html = html
+ self.feed(html)
+ self.close()
+
+class AttrParser(BaseHTMLParser):
"""Modified HTMLParser that isolates a tag with the specified attribute"""
def __init__(self, attribute, value):
self.attribute = attribute
self.result = None
self.started = False
self.depth = {}
- self.html = None
self.watch_startpos = False
self.error_count = 0
- compat_html_parser.HTMLParser.__init__(self)
+ BaseHTMLParser.__init__(self)
def error(self, message):
if self.error_count > 10 or self.started:
self.error_count += 1
self.goahead(1)
- def loads(self, html):
- self.html = html
- self.feed(html)
- self.close()
-
def handle_starttag(self, tag, attrs):
attrs = dict(attrs)
if self.started:
pass
return parser.get_result()
+class MetaParser(BaseHTMLParser):
+ """
+ Modified HTMLParser that isolates a meta tag with the specified name
+ attribute.
+ """
+ def __init__(self, name):
+ BaseHTMLParser.__init__(self)
+ self.name = name
+ self.content = None
+ self.result = None
+
+ def handle_starttag(self, tag, attrs):
+ if tag != 'meta':
+ return
+ attrs = dict(attrs)
+ if attrs.get('name') == self.name:
+ self.result = attrs.get('content')
+
+ def get_result(self):
+ return self.result
+
+def get_meta_content(name, html):
+ """
+ Return the content attribute from the meta tag with the given name attribute.
+ """
+ parser = MetaParser(name)
+ try:
+ parser.loads(html)
+ except compat_html_parser.HTMLParseError:
+ pass
+ return parser.get_result()
+
def clean_html(html):
"""Clean an HTML snippet into a readable string"""
date_str = date_str.replace(',',' ')
# %z (UTC offset) is only supported in python>=3.2
date_str = re.sub(r' (\+|-)[\d]*$', '', date_str)
- format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S', '%d.%m.%Y %H:%M']
+ format_expressions = [
+ '%d %B %Y',
+ '%B %d %Y',
+ '%b %d %Y',
+ '%Y-%m-%d',
+ '%d/%m/%Y',
+ '%Y/%m/%d %H:%M:%S',
+ '%d.%m.%Y %H:%M',
+ '%Y-%m-%dT%H:%M:%SZ',
+ ]
for expression in format_expressions:
try:
upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
return self.start <= date <= self.end
def __str__(self):
return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())
+
+
+def platform_name():
+ """ Returns the platform name as a compat_str """
+ res = platform.platform()
+ if isinstance(res, bytes):
+ res = res.decode(preferredencoding())
+
+ assert isinstance(res, compat_str)
+ return res
+
+
+def write_string(s, out=None):
+ if out is None:
+ out = sys.stderr
+ assert type(s) == type(u'')
+
+ if ('b' in getattr(out, 'mode', '') or
+ sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
+ s = s.encode(preferredencoding(), 'ignore')
+ out.write(s)
+ out.flush()
+
+
+def bytes_to_intlist(bs):
+ if not bs:
+ return []
+ if isinstance(bs[0], int): # Python 3
+ return list(bs)
+ else:
+ return [ord(c) for c in bs]
+
+
+def intlist_to_bytes(xs):
+ if not xs:
+ return b''
+ if isinstance(chr(0), bytes): # Python 2
+ return ''.join([chr(x) for x in xs])
+ else:
+ return bytes(xs)