#!/usr/bin/env python
# -*- coding: utf-8 -*-
+import contextlib
import ctypes
import datetime
import email.utils
import errno
+import getpass
import gzip
import itertools
import io
import subprocess
import sys
import traceback
+import xml.etree.ElementTree
import zlib
try:
except NameError:
compat_chr = chr
+try:
+ from xml.etree.ElementTree import ParseError as compat_xml_parse_error
+except ImportError: # Python 2.6
+ from xml.parsers.expat import ExpatError as compat_xml_parse_error
+
def compat_ord(c):
if type(c) is int: return c
else: return ord(c)
def unified_strdate(date_str):
"""Return a string with the date in the format YYYYMMDD"""
+
+ if date_str is None:
+ return None
+
upload_date = None
#Replace commas
date_str = date_str.replace(',', ' ')
'%B %d %Y',
'%b %d %Y',
'%Y-%m-%d',
+ '%d.%m.%Y',
'%d/%m/%Y',
'%Y/%m/%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S',
'%d.%m.%Y %H:%M',
+ '%d.%m.%Y %H.%M',
'%Y-%m-%dT%H:%M:%SZ',
'%Y-%m-%dT%H:%M:%S.%fZ',
'%Y-%m-%dT%H:%M:%S.%f0Z',
'%Y-%m-%dT%H:%M:%S',
+ '%Y-%m-%dT%H:%M:%S.%f',
'%Y-%m-%dT%H:%M',
]
for expression in format_expressions:
else:
struct_pack = struct.pack
struct_unpack = struct.unpack
+
+
+def read_batch_urls(batch_fd):
+ def fixup(url):
+ if not isinstance(url, compat_str):
+ url = url.decode('utf-8', 'replace')
+ BOM_UTF8 = u'\xef\xbb\xbf'
+ if url.startswith(BOM_UTF8):
+ url = url[len(BOM_UTF8):]
+ url = url.strip()
+ if url.startswith(('#', ';', ']')):
+ return False
+ return url
+
+ with contextlib.closing(batch_fd) as fd:
+ return [url for url in map(fixup, fd) if url]
+
+
+def urlencode_postdata(*args, **kargs):
+ return compat_urllib_parse.urlencode(*args, **kargs).encode('ascii')
+
+
+def parse_xml(s):
+ class TreeBuilder(xml.etree.ElementTree.TreeBuilder):
+ def doctype(self, name, pubid, system):
+ pass # Ignore doctypes
+
+ parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder())
+ kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {}
+ return xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
+
+
+if sys.version_info < (3, 0) and sys.platform == 'win32':
+ def compat_getpass(prompt, *args, **kwargs):
+ if isinstance(prompt, compat_str):
+ prompt = prompt.encode(preferredencoding())
+ return getpass.getpass(prompt, *args, **kwargs)
+else:
+ compat_getpass = getpass.getpass
+
+
+US_RATINGS = {
+ 'G': 0,
+ 'PG': 10,
+ 'PG-13': 13,
+ 'R': 16,
+ 'NC': 18,
+}