pull python-ox changes

This commit is contained in:
j 2014-10-04 21:08:57 +02:00
parent a04e0ede04
commit 7040fdd564
13 changed files with 75 additions and 57 deletions

View file

@ -1,7 +1,11 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4 # vi:si:et:sw=4:sts=4:ts=4
# GPL 2011 # GPL 2011
__version__ = '2.1.1' try:
from . import __version
__version__ = __version.VERSION
except:
__version__ = '2.1.x'
from . import cache from . import cache
from . import js from . import js

View file

@ -0,0 +1 @@
VERSION="2.1.670"

View file

@ -5,7 +5,7 @@ from __future__ import with_statement
from six.moves import http_cookiejar as cookielib from six.moves import http_cookiejar as cookielib
import gzip import gzip
from six import StringIO from six import BytesIO, PY2
from six.moves import urllib from six.moves import urllib
from types import MethodType from types import MethodType
@ -30,7 +30,7 @@ class API(object):
else: else:
self._cj = cookielib.CookieJar() self._cj = cookielib.CookieJar()
self._opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(self._cj), self._opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(self._cj),
urllib.HTTPHandler(debuglevel=self.debuglevel)) urllib.request.HTTPHandler(debuglevel=self.debuglevel))
self._opener.addheaders = [ self._opener.addheaders = [
('User-Agent', '%s/%s' % (self.__name__, self.__version__)) ('User-Agent', '%s/%s' % (self.__name__, self.__version__))
] ]
@ -45,7 +45,10 @@ class API(object):
def _add_method(self, method, name): def _add_method(self, method, name):
if name is None: if name is None:
name = method.func_name name = method.func_name
setattr(self, name, MethodType(method, self, type(self))) if PY2:
setattr(self, name, MethodType(method, self, type(self)))
else:
setattr(self, name, MethodType(method, self))
def _add_action(self, action): def _add_action(self, action):
def method(self, *args, **kw): def method(self, *args, **kw):
@ -57,22 +60,30 @@ class API(object):
return self._request(action, kw) return self._request(action, kw)
if 'doc' in self._properties[action]: if 'doc' in self._properties[action]:
method.__doc__ = self._properties[action]['doc'] method.__doc__ = self._properties[action]['doc']
method.func_name = str(action) if PY2:
method.func_name = str(action)
else:
method.func_name = action
self._add_method(method, action) self._add_method(method, action)
def _json_request(self, url, form): def _json_request(self, url, form):
result = {} result = {}
try: try:
body = str(form) body = form.body()
request = urllib.reuqest.Request(str(url)) if PY2:
request.add_header('Content-type', form.get_content_type()) if not isinstance(url, bytes):
url = url.encode('utf-8')
request = urllib.request.Request(url)
request.add_data(body)
else:
request = urllib.request.Request(url, data=body, method='POST')
request.add_header('Content-Type', form.get_content_type())
request.add_header('Content-Length', str(len(body))) request.add_header('Content-Length', str(len(body)))
request.add_header('Accept-Encoding', 'gzip, deflate') request.add_header('Accept-Encoding', 'gzip, deflate')
request.add_data(body)
f = self._opener.open(request) f = self._opener.open(request)
result = f.read() result = f.read()
if f.headers.get('content-encoding', None) == 'gzip': if f.headers.get('content-encoding', None) == 'gzip':
result = gzip.GzipFile(fileobj=StringIO.StringIO(result)).read() result = gzip.GzipFile(fileobj=BytesIO(result)).read()
result = result.decode('utf-8') result = result.decode('utf-8')
return json.loads(result) return json.loads(result)
except urllib.error.HTTPError as e: except urllib.error.HTTPError as e:

View file

@ -10,6 +10,7 @@ import os
from six import BytesIO from six import BytesIO
import time import time
from six.moves import urllib from six.moves import urllib
from six import PY2
import sqlite3 import sqlite3
from .utils import json from .utils import json
@ -24,6 +25,7 @@ COMPRESS_TYPES = (
'text/html', 'text/html',
'text/plain', 'text/plain',
'text/xml', 'text/xml',
'application/json',
'application/xhtml+xml', 'application/xhtml+xml',
'application/x-javascript', 'application/x-javascript',
'application/javascript', 'application/javascript',
@ -117,9 +119,8 @@ def save_url(url, filename, overwrite=False):
if not os.path.exists(dirname): if not os.path.exists(dirname):
os.makedirs(dirname) os.makedirs(dirname)
data = read_url(url) data = read_url(url)
f = open(filename, 'w') with open(filename, 'wb') as f:
f.write(data) f.write(data)
f.close()
def cache_path(): def cache_path():
return os.environ.get('oxCACHE', os.path.expanduser('~/.ox/cache')) return os.environ.get('oxCACHE', os.path.expanduser('~/.ox/cache'))
@ -203,7 +204,7 @@ class SQLiteCache(Cache):
elif value == 'data': elif value == 'data':
if row[1] == 1: if row[1] == 1:
r = zlib.decompress(r) r = zlib.decompress(r)
else: elif PY2:
r = str(r) r = str(r)
break break
@ -290,7 +291,7 @@ class FileCache(Cache):
if value == 'headers': if value == 'headers':
r = info['headers'] r = info['headers']
else: else:
with open(f) as data: with open(f, 'rb') as data:
r = data.read() r = data.read()
if info['compressed']: if info['compressed']:
r = zlib.decompress(r) r = zlib.decompress(r)
@ -321,9 +322,11 @@ class FileCache(Cache):
if not info['only_headers']: if not info['only_headers']:
if info['compressed']: if info['compressed']:
data = zlib.compress(data) data = zlib.compress(data)
with open(f, 'w') as _f: elif not isinstance(data, str):
data = data.encode('utf-8')
with open(f, 'wb') as _f:
_f.write(data) _f.write(data)
with open(i, 'w') as _i: with open(i, 'wb') as _i:
json.dump(info, _i) json.dump(info, _i)
if cache_path().startswith('fs:'): if cache_path().startswith('fs:'):

View file

@ -8,6 +8,8 @@ import mimetypes
import random import random
import sys import sys
from six import PY2
__all__ = ['MultiPartForm'] __all__ = ['MultiPartForm']
@ -36,19 +38,19 @@ class MultiPartForm(object):
def add_field(self, name, value): def add_field(self, name, value):
"""Add a simple field to the form data.""" """Add a simple field to the form data."""
if isinstance(name, unicode): if isinstance(name, bytes):
name = name.encode('utf-8') name = name.decode('utf-8')
if isinstance(value, unicode): if isinstance(value, bytes):
value = value.encode('utf-8') value = value.decode('utf-8')
self.form_fields.append((name, value)) self.form_fields.append((name, value))
return return
def add_file(self, fieldname, filename, fileHandle, mimetype=None): def add_file(self, fieldname, filename, fileHandle, mimetype=None):
"""Add a file to be uploaded.""" """Add a file to be uploaded."""
if isinstance(fieldname, unicode): if isinstance(fieldname, bytes):
fieldname = fieldname.encode('utf-8') fieldname = fieldname.decode('utf-8')
if isinstance(filename, unicode): if isinstance(filename, bytes):
filename = filename.encode('utf-8') filename = filename.decode('utf-8')
if hasattr(fileHandle, 'read'): if hasattr(fileHandle, 'read'):
body = fileHandle.read() body = fileHandle.read()
@ -60,6 +62,12 @@ class MultiPartForm(object):
return return
def __str__(self): def __str__(self):
body = self.body()
if not PY2:
body = body.decode('utf-8')
return body
def body(self):
"""Return a string representing the form data, including attached files.""" """Return a string representing the form data, including attached files."""
# Build a list of lists, each containing "lines" of the # Build a list of lists, each containing "lines" of the
# request. Each part is separated by a boundary string. # request. Each part is separated by a boundary string.
@ -95,5 +103,6 @@ class MultiPartForm(object):
flattened = list(itertools.chain(*parts)) flattened = list(itertools.chain(*parts))
flattened.append('--' + self.boundary + '--') flattened.append('--' + self.boundary + '--')
flattened.append('') flattened.append('')
return '\r\n'.join(flattened) flattened = [part if isinstance(part, bytes) else part.encode('utf-8') for part in flattened]
return b'\r\n'.join(flattened)

View file

@ -5,7 +5,7 @@ from __future__ import with_statement, print_function
import os import os
import gzip import gzip
import re import re
from six import BytesIO from six import BytesIO, PY3
import struct import struct
from six.moves import urllib from six.moves import urllib
@ -51,6 +51,8 @@ def open_url(url, data=None, headers=DEFAULT_HEADERS):
if isinstance(url, bytes): if isinstance(url, bytes):
url = url.decode('utf-8') url = url.decode('utf-8')
url = url.replace(' ', '%20') url = url.replace(' ', '%20')
if data and PY3 and not isinstance(data, bytes):
data = data.encode('utf-8')
req = urllib.request.Request(url, data, headers) req = urllib.request.Request(url, data, headers)
return urllib.request.urlopen(req) return urllib.request.urlopen(req)
@ -104,9 +106,8 @@ def save_url(url, filename, overwrite=False):
if not os.path.exists(dirname): if not os.path.exists(dirname):
os.makedirs(dirname) os.makedirs(dirname)
data = read_url(url) data = read_url(url)
f = open(filename, 'w') with open(filename, 'wb') as f:
f.write(data) f.write(data)
f.close()
def oshash(url): def oshash(url):
def get_size(url): def get_size(url):

View file

@ -9,7 +9,6 @@ import unicodedata
from six.moves import urllib from six.moves import urllib
from six import string_types from six import string_types
from .. import find_re, strip_tags, decode_html from .. import find_re, strip_tags, decode_html
from .. import cache from .. import cache

View file

@ -2,7 +2,7 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import print_function from __future__ import print_function
import re import re
import urllib from six.moves import urllib
from ox.cache import read_url from ox.cache import read_url
from ox.html import decode_html, strip_tags from ox.html import decode_html, strip_tags

View file

@ -1,7 +1,8 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4 # vi:si:et:sw=4:sts=4:ts=4
import re import re
from urllib import quote
from six.moves.urllib.parse import quote
from lxml.html import document_fromstring from lxml.html import document_fromstring
from ox.cache import read_url from ox.cache import read_url

View file

@ -3,7 +3,7 @@
from datetime import datetime from datetime import datetime
import re import re
import socket import socket
from urllib import quote from six.moves.urllib.parse import quote
from ox.cache import read_url from ox.cache import read_url
from ox import find_re, cache, strip_tags, decode_html, get_torrent_info, int_value, normalize_newlines from ox import find_re, cache, strip_tags, decode_html, get_torrent_info, int_value, normalize_newlines

View file

@ -2,9 +2,8 @@
# vi:si:et:sw=4:sts=4:ts=4 # vi:si:et:sw=4:sts=4:ts=4
from datetime import datetime from datetime import datetime
import re import re
import socket
from urllib import quote, urlencode from six.moves.urllib.parse import quote
from urllib2 import URLError
from ox import find_re, cache, strip_tags, decode_html, get_torrent_info, normalize_newlines from ox import find_re, cache, strip_tags, decode_html, get_torrent_info, normalize_newlines
from ox.normalize import normalize_imdbid from ox.normalize import normalize_imdbid

View file

@ -2,7 +2,7 @@
# vi:si:et:sw=4:sts=4:ts=4 # vi:si:et:sw=4:sts=4:ts=4
import re import re
from datetime import datetime from datetime import datetime
from urllib import quote from six.moves.urllib.parse import quote
import lxml.html import lxml.html
import ox import ox

View file

@ -1,27 +1,17 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4 # vi:si:et:sw=4:sts=4:ts=4
import re
from StringIO import StringIO import json
import xml.etree.ElementTree as ET
from ox.cache import read_url from ox.cache import read_url
from ox import find_string, find_re
def get_data(id): def get_data(id):
url = 'http://www.vimeo.com/moogaloop/load/clip:%s' %id url = 'http://vimeo.com/api/v2/video/%s.json' % id
xml = read_url(url) data = json.loads(read_url(url).decode('utf-8'))[0]
tree = ET.parse(StringIO(xml))
request_signature = tree.find('request_signature').text
request_signature_expires = tree.find('request_signature_expires').text
data = {} url = 'http://player.vimeo.com/video/%s/config?autoplay=0&byline=0&bypass_privacy=1&context=clip.main&default_to_hd=1&portrait=0' % id
video_url = "http://www.vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=" % \ info = json.loads(read_url(url).decode('utf-8'))
(id, request_signature, request_signature_expires) data['video'] = info['request']['files']['h264']
data['video_sd'] = video_url + 'sd'
data['video_hd'] = video_url + 'hd'
video = tree.find('video')
for key in ('caption', 'width', 'height', 'duration', 'thumbnail'):
data[key] = video.find(key).text
return data return data