summaryrefslogtreecommitdiffstats
path: root/module/plugins/internal/SimpleHoster.py
diff options
context:
space:
mode:
Diffstat (limited to 'module/plugins/internal/SimpleHoster.py')
-rw-r--r--module/plugins/internal/SimpleHoster.py680
1 files changed, 506 insertions, 174 deletions
diff --git a/module/plugins/internal/SimpleHoster.py b/module/plugins/internal/SimpleHoster.py
index f10433e78..d9732d063 100644
--- a/module/plugins/internal/SimpleHoster.py
+++ b/module/plugins/internal/SimpleHoster.py
@@ -1,36 +1,51 @@
# -*- coding: utf-8 -*-
-"""
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 3 of the License,
- or (at your option) any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, see <http://www.gnu.org/licenses/>.
-
- @author: zoidberg
-"""
-from urlparse import urlparse
import re
+
+from os.path import exists
from time import time
+from urllib import unquote
+from urlparse import urljoin, urlparse
-from module.plugins.Hoster import Hoster
-from module.utils import html_unescape, fixup, parseFileSize
-from module.network.RequestFactory import getURL
+from module.PyFile import statusMap as _statusMap
from module.network.CookieJar import CookieJar
+from module.network.RequestFactory import getURL
+from module.plugins.Hoster import Hoster
+from module.plugins.Plugin import Fail
+from module.utils import fixup, fs_encode, parseFileSize
+
+
+#@TODO: Adapt and move to PyFile in 0.4.10
+statusMap = dict((v, k) for k, v in _statusMap.iteritems())
+
+
+#@TODO: Remove in 0.4.10 and redirect to self.error instead
+def _error(self, reason, type):
+ if not reason and not type:
+ type = "unknown"
+
+ msg = _("%s error") % type.strip().capitalize() if type else _("Error")
+ msg += ": %s" % reason.strip() if reason else ""
+ msg += _(" | Plugin may be out of date")
+
+ raise Fail(msg)
+
+
+#@TODO: Remove in 0.4.10
+def _wait(self, seconds, reconnect):
+ if seconds:
+ self.setWait(int(seconds) + 1)
+
+ if reconnect is not None:
+ self.wantReconnect = reconnect
+
+ super(SimpleHoster, self).wait()
def replace_patterns(string, ruleslist):
for r in ruleslist:
rf, rt = r
string = re.sub(rf, rt, string)
- #self.logDebug(rf, rt, string)
return string
@@ -46,23 +61,24 @@ def parseHtmlTagAttrValue(attr_name, tag):
return m.group(2) if m else None
-def parseHtmlForm(attr_str, html, input_names=None):
- for form in re.finditer(r"(?P<tag><form[^>]*%s[^>]*>)(?P<content>.*?)</?(form|body|html)[^>]*>" % attr_str,
+def parseHtmlForm(attr_str, html, input_names={}):
+ for form in re.finditer(r"(?P<TAG><form[^>]*%s[^>]*>)(?P<CONTENT>.*?)</?(form|body|html)[^>]*>" % attr_str,
html, re.S | re.I):
inputs = {}
- action = parseHtmlTagAttrValue("action", form.group('tag'))
- for inputtag in re.finditer(r'(<(input|textarea)[^>]*>)([^<]*(?=</\2)|)', form.group('content'), re.S | re.I):
+ action = parseHtmlTagAttrValue("action", form.group('TAG'))
+
+ for inputtag in re.finditer(r'(<(input|textarea)[^>]*>)([^<]*(?=</\2)|)', form.group('CONTENT'), re.S | re.I):
name = parseHtmlTagAttrValue("name", inputtag.group(1))
if name:
value = parseHtmlTagAttrValue("value", inputtag.group(1))
- if value is None:
+ if not value:
inputs[name] = inputtag.group(3) or ''
else:
inputs[name] = value
- if isinstance(input_names, dict):
+ if input_names:
# check input attributes
- for key, val in input_names.items():
+ for key, val in input_names.iteritems():
if key in inputs:
if isinstance(val, basestring) and inputs[key] == val:
continue
@@ -70,219 +86,535 @@ def parseHtmlForm(attr_str, html, input_names=None):
continue
elif hasattr(val, "search") and re.match(val, inputs[key]):
continue
- break # attibute value does not match
+ break #: attibute value does not match
else:
- break # attibute name does not match
+ break #: attibute name does not match
else:
- return action, inputs # passed attribute check
+ return action, inputs #: passed attribute check
else:
# no attribute check
return action, inputs
- return {}, None # no matching form found
+ return {}, None #: no matching form found
-def parseFileInfo(self, url='', html=''):
- info = {"name": url, "size": 0, "status": 3}
+#: Deprecated
+def parseFileInfo(plugin, url="", html=""):
+ if hasattr(plugin, "getInfo"):
+ info = plugin.getInfo(url, html)
+ res = info['name'], info['size'], info['status'], info['url']
+ else:
+ res = urlparse(unquote(url)).path.split('/')[-1] or _("Unknown"), 0, 3, url
- if hasattr(self, "pyfile"):
- url = self.pyfile.url
+ return res
- if hasattr(self, "req") and self.req.http.code == '404':
- info['status'] = 1
+
+#@TODO: Remove in 0.4.10
+#@NOTE: Every plugin must have own parseInfos classmethod to work with 0.4.10
+def create_getInfo(plugin):
+ if hasattr(plugin, "parseInfos"):
+ fn = lambda urls: [(info['name'], info['size'], info['status'], info['url']) for info in plugin.parseInfos(urls)]
else:
- if not html and hasattr(self, "html"):
- html = self.html
- if isinstance(self.SH_BROKEN_ENCODING, (str, unicode)):
- html = unicode(html, self.SH_BROKEN_ENCODING)
- if hasattr(self, "html"):
- self.html = html
-
- if hasattr(self, "FILE_OFFLINE_PATTERN") and re.search(self.FILE_OFFLINE_PATTERN, html):
- # File offline
- info['status'] = 1
- else:
- online = False
- try:
- info.update(re.match(self.__pattern__, url).groupdict())
- except:
- pass
+ fn = lambda urls: [parseFileInfo(url) for url in urls]
- for pattern in ("FILE_INFO_PATTERN", "FILE_NAME_PATTERN", "FILE_SIZE_PATTERN"):
- try:
- info.update(re.search(getattr(self, pattern), html).groupdict())
- online = True
- except AttributeError:
- continue
+ return fn
- if online:
- # File online, return name and size
- info['status'] = 2
- if 'N' in info:
- info['name'] = replace_patterns(info['N'], self.FILE_NAME_REPLACEMENTS)
- if 'S' in info:
- size = replace_patterns(info['S'] + info['U'] if 'U' in info else info['S'],
- self.FILE_SIZE_REPLACEMENTS)
- info['size'] = parseFileSize(size)
- elif isinstance(info['size'], (str, unicode)):
- if 'units' in info:
- info['size'] += info['units']
- info['size'] = parseFileSize(info['size'])
- if hasattr(self, "file_info"):
- self.file_info = info
+def timestamp():
+ return int(time() * 1000)
- return info['name'], info['size'], info['status'], url
+#@TODO: Move to hoster class in 0.4.10
+def _isDirectLink(self, url, resumable=False):
+ link = ""
-def create_getInfo(plugin):
- def getInfo(urls):
- for url in urls:
- cj = CookieJar(plugin.__name__)
- if isinstance(plugin.SH_COOKIES, list):
- set_cookies(cj, plugin.SH_COOKIES)
- file_info = parseFileInfo(plugin, url, getURL(replace_patterns(url, plugin.FILE_URL_REPLACEMENTS),
- decode=not plugin.SH_BROKEN_ENCODING, cookies=cj))
- yield file_info
+ for i in xrange(5 if resumable else 1):
+ header = self.load(url, ref=True, cookies=True, just_header=True, decode=True)
- return getInfo
+ if 'content-disposition' in header or 'content-length' in header:
+ link = url
+ elif 'location' in header and header['location']:
+ location = header['location']
-def timestamp():
- return int(time() * 1000)
+ if not urlparse(location).scheme:
+ p = urlparse(url)
+ base = "%s://%s" % (p.scheme, p.netloc)
+ location = urljoin(base, location)
+ if 'code' in header and header['code'] == 302:
+ link = location
-class PluginParseError(Exception):
- def __init__(self, msg):
- Exception.__init__(self)
- self.value = 'Parse error (%s) - plugin may be out of date' % msg
+ elif resumable:
+ url = location
+ self.logDebug("Redirect #%d to: %s" % (++i, location))
+ continue
- def __str__(self):
- return repr(self.value)
+ elif 'content-type' in header and header['content-type' ] and "html" not in header['content-type']:
+ link = url
+
+ break
+ else:
+ self.logError(_("Too many redirects"))
+
+ return link
+
+
+def secondsToMidnight(gmt=0):
+ now = datetime.utcnow() + timedelta(hours=gmt)
+
+ if now.hour is 0 and now.minute < 10:
+ midnight = now
+ else:
+ midnight = now + timedelta(days=1)
+
+ td = midnight.replace(hour=0, minute=10, second=0, microsecond=0) - now
+
+ if hasattr(td, 'total_seconds'):
+ res = td.total_seconds()
+ else: #@NOTE: work-around for python 2.5 and 2.6 missing timedelta.total_seconds
+ res = (td.microseconds + (td.seconds + td.days * 24 * 3600) * 10**6) / 10**6
+
+ return int(res)
class SimpleHoster(Hoster):
- __name__ = "SimpleHoster"
- __version__ = "0.33"
- __pattern__ = None
- __type__ = "hoster"
+ __name__ = "SimpleHoster"
+ __type__ = "hoster"
+ __version__ = "0.82"
+
+ __pattern__ = r'^unmatchable$'
+
__description__ = """Simple hoster plugin"""
- __author_name__ = ("zoidberg", "stickell")
- __author_mail__ = ("zoidberg@mujmail.cz", "l.stickell@yahoo.it")
+ __license__ = "GPLv3"
+ __authors__ = [("zoidberg", "zoidberg@mujmail.cz"),
+ ("stickell", "l.stickell@yahoo.it"),
+ ("Walter Purcaro", "vuolter@gmail.com")]
+
+
"""
- These patterns should be defined by each hoster:
- FILE_INFO_PATTERN = r'(?P<N>file_name) (?P<S>file_size) (?P<U>units)'
- or FILE_NAME_PATTERN = r'(?P<N>file_name)'
- and FILE_SIZE_PATTERN = r'(?P<S>file_size) (?P<U>units)'
- FILE_OFFLINE_PATTERN = r'File (deleted|not found)'
- TEMP_OFFLINE_PATTERN = r'Server maintainance'
-
- You can also define a PREMIUM_ONLY_PATTERN to detect links that can be downloaded only with a premium account.
+ Info patterns should be defined by each hoster:
+
+ INFO_PATTERN: (optional) Name and Size of the file
+ example: INFO_PATTERN = r'(?P<N>file_name) (?P<S>file_size) (?P<U>size_unit)'
+ or
+ NAME_PATTERN: (optional) Name that will be set for the file
+ example: NAME_PATTERN = r'(?P<N>file_name)'
+ SIZE_PATTERN: (optional) Size that will be checked for the file
+ example: SIZE_PATTERN = r'(?P<S>file_size) (?P<U>size_unit)'
+
+ HASHSUM_PATTERN: (optional) Hash code and type of the file
+ example: HASHSUM_PATTERN = r'(?P<H>hash_code) (?P<T>MD5)'
+
+ OFFLINE_PATTERN: (optional) Check if the page is unreachable
+ example: OFFLINE_PATTERN = r'File (deleted|not found)'
+
+ TEMP_OFFLINE_PATTERN: (optional) Check if the page is temporarily unreachable
+ example: TEMP_OFFLINE_PATTERN = r'Server (maintenance|maintainance)'
+
+
+ Error handling patterns are all optional:
+
+ WAIT_PATTERN: (optional) Detect waiting time
+ example: WAIT_PATTERN = r''
+
+ PREMIUM_ONLY_PATTERN: (optional) Check if the file can be downloaded only with a premium account
+ example: PREMIUM_ONLY_PATTERN = r'Premium account required'
+
+ ERROR_PATTERN: (optional) Detect any error preventing download
+ example: ERROR_PATTERN = r''
+
+
+ Instead overriding handleFree and handlePremium methods you can define the following patterns for direct download:
+
+ LINK_FREE_PATTERN: (optional) group(1) should be the direct link for free download
+ example: LINK_FREE_PATTERN = r'<div class="link"><a href="(.+?)"'
+
+ LINK_PREMIUM_PATTERN: (optional) group(1) should be the direct link for premium download
+ example: LINK_PREMIUM_PATTERN = r'<div class="link"><a href="(.+?)"'
"""
- FILE_SIZE_REPLACEMENTS = []
- FILE_NAME_REPLACEMENTS = [("&#?\w+;", fixup)]
- FILE_URL_REPLACEMENTS = []
+ NAME_REPLACEMENTS = [("&#?\w+;", fixup)]
+ SIZE_REPLACEMENTS = []
+ URL_REPLACEMENTS = []
+
+ TEXT_ENCODING = False #: Set to True or encoding name if encoding value in http header is not correct
+ COOKIES = True #: or False or list of tuples [(domain, name, value)]
+ CHECK_TRAFFIC = False #: Set to True to force checking traffic left for premium account
+ DIRECT_LINK = None #: Set to True to looking for direct link (as defined in handleDirect method), set to None to do it if self.account is True else False
+ MULTI_HOSTER = False #: Set to True to leech other hoster link (as defined in handleMulti method)
+
+
+ @classmethod
+ def parseInfos(cls, urls):
+ for url in urls:
+ url = replace_patterns(url, cls.FILE_URL_REPLACEMENTS if hasattr(cls, "FILE_URL_REPLACEMENTS") else cls.URL_REPLACEMENTS) #@TODO: Remove FILE_URL_REPLACEMENTS check in 0.4.10
+ yield cls.getInfo(url)
+
+
+ @classmethod
+ def getInfo(cls, url="", html=""):
+ info = {'name': urlparse(unquote(url)).path.split('/')[-1] or _("Unknown"), 'size': 0, 'status': 3, 'url': url}
+ online = False
+
+ try:
+ info['pattern'] = re.match(cls.__pattern__, url).groupdict() #: pattern groups will be saved here, please save api stuff to info['api']
+ except Exception:
+ pass
+
+ if not html:
+ try:
+ if not url:
+ info['error'] = "missing url"
+ info['status'] = 1
+ raise
+
+ if _isDirectLink(url):
+ info['error'] = "direct link"
+ info['status'] = 2
+ raise
+
+ try:
+ html = getURL(url, cookies=cls.COOKIES, decode=not cls.TEXT_ENCODING)
+
+ if isinstance(cls.TEXT_ENCODING, basestring):
+ html = unicode(html, cls.TEXT_ENCODING)
+
+ except BadHeader, e:
+ info['error'] = "%d: %s" % (e.code, e.content)
+
+ if e.code is 404:
+ info['status'] = 1
+ raise
+
+ if e.code is 503:
+ info['status'] = 6
+ raise
+ except:
+ return info
+
+ if hasattr(cls, "OFFLINE_PATTERN") and re.search(cls.OFFLINE_PATTERN, html):
+ info['status'] = 1
+
+ elif hasattr(cls, "FILE_OFFLINE_PATTERN") and re.search(cls.FILE_OFFLINE_PATTERN, html): #@TODO: Remove in 0.4.10
+ info['status'] = 1
+
+ elif hasattr(cls, "TEMP_OFFLINE_PATTERN") and re.search(cls.TEMP_OFFLINE_PATTERN, html):
+ info['status'] = 6
+
+ else:
+ if not 'pattern' in info:
+ info['pattern'] = {}
+
+ for pattern in ("FILE_INFO_PATTERN", "INFO_PATTERN",
+ "FILE_NAME_PATTERN", "NAME_PATTERN",
+ "FILE_SIZE_PATTERN", "SIZE_PATTERN",
+ "HASHSUM_PATTERN"): #@TODO: Remove old patterns starting with "FILE_" in 0.4.10
+ try:
+ attr = getattr(cls, pattern)
+ pdict = re.search(attr, html).groupdict()
+
+ if all(True for k in pdict if k not in info['pattern']):
+ info['pattern'].update(pdict)
+
+ except AttributeError:
+ continue
+
+ else:
+ online = True
+
+ if not info['pattern']:
+ info.pop('pattern', None)
+
+ if online:
+ info['status'] = 2
+
+ if 'N' in info['pattern']:
+ info['name'] = replace_patterns(unquote(info['pattern']['N'].strip()),
+ cls.FILE_NAME_REPLACEMENTS if hasattr(cls, "FILE_NAME_REPLACEMENTS") else cls.NAME_REPLACEMENTS) #@TODO: Remove FILE_NAME_REPLACEMENTS check in 0.4.10
+
+ if 'S' in info['pattern']:
+ size = replace_patterns(info['pattern']['S'] + info['pattern']['U'] if 'U' in info['pattern'] else info['pattern']['S'],
+ cls.FILE_SIZE_REPLACEMENTS if hasattr(cls, "FILE_SIZE_REPLACEMENTS") else cls.SIZE_REPLACEMENTS) #@TODO: Remove FILE_SIZE_REPLACEMENTS check in 0.4.10
+ info['size'] = parseFileSize(size)
+
+ elif isinstance(info['size'], basestring):
+ unit = info['units'] if 'units' in info else None
+ info['size'] = parseFileSize(info['size'], unit)
+
+ if 'H' in info['pattern']:
+ hashtype = info['pattern']['T'] if 'T' in info['pattern'] else "hash"
+ info[hashtype] = info['pattern']['H']
- SH_BROKEN_ENCODING = False # Set to True or encoding name if encoding in http header is not correct
- SH_COOKIES = True # or False or list of tuples [(domain, name, value)]
- SH_CHECK_TRAFFIC = False # True = force check traffic left for a premium account
+ return info
- def init(self):
- self.file_info = {}
def setup(self):
self.resumeDownload = self.multiDL = self.premium
- if isinstance(self.SH_COOKIES, list):
- set_cookies(self.req.cj, self.SH_COOKIES)
- def process(self, pyfile):
- pyfile.url = replace_patterns(pyfile.url, self.FILE_URL_REPLACEMENTS)
+
+ def prepare(self):
+ self.info = {}
+ self.link = "" #@TODO: Move to hoster class in 0.4.10
+ self.directDL = False #@TODO: Move to hoster class in 0.4.10
+ self.multihost = False #@TODO: Move to hoster class in 0.4.10
+
self.req.setOption("timeout", 120)
- # Due to a 0.4.9 core bug self.load would keep previous cookies even if overridden by cookies parameter.
- # Workaround using getURL. Can be reverted in 0.5 as the cookies bug has been fixed.
- self.html = getURL(pyfile.url, decode=not self.SH_BROKEN_ENCODING, cookies=self.SH_COOKIES)
- premium_only = hasattr(self, 'PREMIUM_ONLY_PATTERN') and re.search(self.PREMIUM_ONLY_PATTERN, self.html)
- if not premium_only: # Usually premium only pages doesn't show the file information
- self.getFileInfo()
-
- if self.premium and (not self.SH_CHECK_TRAFFIC or self.checkTrafficLeft()):
- self.handlePremium()
- elif premium_only:
- self.fail("This link require a premium account")
+
+ if isinstance(self.COOKIES, list):
+ set_cookies(self.req.cj, self.COOKIES)
+
+ if (self.MULTI_HOSTER
+ and (self.__pattern__ != self.core.pluginManager.hosterPlugins[self.__name__]['pattern']
+ or re.match(self.__pattern__, self.pyfile.url) is None)):
+ self.multihost = True
+ return
+
+ if self.DIRECT_LINK is None:
+ self.directDL = bool(self.account)
else:
- # This line is required due to the getURL workaround. Can be removed in 0.5
- self.html = self.load(pyfile.url, decode=not self.SH_BROKEN_ENCODING, cookies=self.SH_COOKIES)
- self.handleFree()
+ self.directDL = self.DIRECT_LINK
- def load(self, url, get={}, post={}, ref=True, cookies=True, just_header=False, decode=False):
- if type(url) == unicode:
- url = url.encode('utf8')
- return Hoster.load(self, url=url, get=get, post=post, ref=ref, cookies=cookies,
- just_header=just_header, decode=decode)
+ self.pyfile.url = replace_patterns(self.pyfile.url,
+ self.FILE_URL_REPLACEMENTS if hasattr(self, "FILE_URL_REPLACEMENTS") else self.URL_REPLACEMENTS) #@TODO: Remove FILE_URL_REPLACEMENTS check in 0.4.10
+
+
+ def preload(self):
+ self.html = self.load(self.pyfile.url, cookies=bool(self.COOKIES), decode=not self.TEXT_ENCODING)
+
+ if isinstance(self.TEXT_ENCODING, basestring):
+ self.html = unicode(self.html, self.TEXT_ENCODING)
+
+
+ def process(self, pyfile):
+ self.prepare()
+ self.checkInfo()
+
+ if self.directDL:
+ self.logDebug("Looking for direct download link...")
+ self.handleDirect()
+
+ if self.multihost and not self.link and not self.lastDownload:
+ self.logDebug("Looking for leeched download link...")
+ self.handleMulti()
+
+ if not self.link and not self.lastDownload:
+ self.MULTI_HOSTER = False
+ self.retry(1, reason="Multi hoster fails")
+
+ if not self.link and not self.lastDownload:
+ self.preload()
+ self.checkInfo()
+
+ if self.html is None:
+ self.fail(_("No html retrieved"))
+
+ if self.premium and (not self.CHECK_TRAFFIC or self.checkTrafficLeft()):
+ self.logDebug("Handled as premium download")
+ self.handlePremium()
+
+ else:
+ self.logDebug("Handled as free download")
+ self.handleFree()
+
+ self.downloadLink(self.link)
+ self.checkFile()
+
+
+ def downloadLink(self, link):
+ if link and isinstance(link, basestring):
+ self.correctCaptcha()
+ self.download(link, disposition=True)
+
+
+ def checkFile(self):
+ if self.cTask and not self.lastDownload:
+ self.invalidCaptcha()
+ self.retry(10, reason=_("Wrong captcha"))
+
+ elif not self.lastDownload or not exists(fs_encode(self.lastDownload)):
+ errmsg = _("No file downloaded")
+ if 'error' in self.info:
+ self.fail(errmsg, self.info['error'])
+ else:
+ self.fail(errmsg)
+
+ else:
+ rules = {'empty file': re.compile(r"^$")}
+
+ if hasattr(self, 'ERROR_PATTERN'):
+ rules['error'] = re.compile(self.ERROR_PATTERN)
+
+ check = self.checkDownload(rules)
+ if check: #@TODO: Move to hoster in 0.4.10
+ errmsg = check.strip().capitalize() + (" | " + self.lastCheck.strip() if self.lastCheck else "")
+ self.retry(10, 60, errmsg)
- def getFileInfo(self):
- self.logDebug("URL: %s" % self.pyfile.url)
- if hasattr(self, "TEMP_OFFLINE_PATTERN") and re.search(self.TEMP_OFFLINE_PATTERN, self.html):
- self.tempOffline()
- name, size, status = parseFileInfo(self)[:3]
+ def checkErrors(self):
+ if hasattr(self, 'PREMIUM_ONLY_PATTERN') and self.premium and re.search(self.PREMIUM_ONLY_PATTERN, self.html):
+ self.fail(_("Link require a premium account to be handled"))
- if status == 1:
+ if hasattr(self, 'ERROR_PATTERN'):
+ m = re.search(self.ERROR_PATTERN, self.html)
+ if m:
+ errmsg = self.info['error'] = m.group(1)
+ self.error(errmsg)
+
+ if hasattr(self, 'WAIT_PATTERN'):
+ m = re.search(self.WAIT_PATTERN, self.html)
+ if m:
+ wait_time = sum([int(v) * {"hr": 3600, "hour": 3600, "min": 60, "sec": 1}[u.lower()] for v, u in
+ re.findall(r'(\d+)\s*(hr|hour|min|sec)', m.group(0), re.I)])
+ self.wait(wait_time, wait_time > 300)
+ return
+
+ self.info.pop('error', None)
+
+
+ def checkStatus(self, getinfo=True):
+ if getinfo:
+ self.updateInfo(self.getInfo(self.pyfile.url, self.html))
+
+ status = self.info['status']
+
+ if status is 1:
self.offline()
- elif status != 2:
- self.logDebug(self.file_info)
- self.parseError('File info')
- if name:
+ elif status is 6:
+ self.tempOffline()
+
+ elif status is not 2:
+ self.logDebug("File status: %s" % statusMap[status],
+ "File info: %s" % self.info)
+
+
+ def checkNameSize(self, getinfo=True):
+ if getinfo:
+ self.updateInfo(self.getInfo(self.pyfile.url, self.html))
+
+ name = self.info['name']
+ size = self.info['size']
+ url = self.info['url']
+
+ if name and name != url:
self.pyfile.name = name
else:
- self.pyfile.name = html_unescape(urlparse(self.pyfile.url).path.split("/")[-1])
+ self.pyfile.name = name = self.info['name'] = urlparse(name).path.split('/')[-1]
- if size:
+ if size > 0:
self.pyfile.size = size
else:
- self.logError("File size not parsed")
+ size = "Unknown"
+
+ self.logDebug("File name: %s" % name,
+ "File size: %s" % size)
+
+
+ def checkInfo(self):
+ self.checkNameSize()
+
+ if self.html:
+ self.checkErrors()
+
+ self.checkNameSize()
+ self.checkStatus(getinfo=False)
+
+
+ #: Deprecated
+ def getFileInfo(self):
+ self.info = {}
+ self.checkInfo()
+ return self.info
+
+
+ def updateInfo(self, info):
+ self.logDebug(_("File info (BEFORE): %s") % self.info)
+ self.info.update(info)
+ self.logDebug(_("File info (AFTER): %s") % self.info)
+
+
+ def handleDirect(self):
+ link = _isDirectLink(self, self.pyfile.url, self.resumeDownload)
+
+ if link:
+ self.logInfo(_("Direct download link detected"))
+
+ self.link = link
+ else:
+ self.logDebug(_("Direct download link not found"))
+
+
+ def handleMulti(self): #: Multi-hoster handler
+ pass
- self.logDebug("FILE NAME: %s FILE SIZE: %s" % (self.pyfile.name, self.pyfile.size))
- return self.file_info
def handleFree(self):
- self.fail("Free download not implemented")
+ if not hasattr(self, 'LINK_FREE_PATTERN'):
+ self.fail(_("Free download not implemented"))
+
+ try:
+ m = re.search(self.LINK_FREE_PATTERN, self.html)
+ if m is None:
+ self.error(_("Free download link not found"))
+
+ self.link = m.group(1)
+
+ except Exception, e:
+ self.fail(e)
+
def handlePremium(self):
- self.fail("Premium download not implemented")
+ if not hasattr(self, 'LINK_PREMIUM_PATTERN'):
+ self.fail(_("Premium download not implemented"))
+
+ try:
+ m = re.search(self.LINK_PREMIUM_PATTERN, self.html)
+ if m is None:
+ self.error(_("Premium download link not found"))
+
+ self.link = m.group(1)
+
+ except Exception, e:
+ self.fail(e)
- def parseError(self, msg):
- raise PluginParseError(msg)
def longWait(self, wait_time=None, max_tries=3):
if wait_time and isinstance(wait_time, (int, long, float)):
- time_str = "%dh %dm" % divmod(wait_time / 60, 60)
+ time_str = "%dh %dm" % divmod(wait_time / 60, 60)
else:
wait_time = 900
- time_str = "(unknown time)"
+ time_str = _("(unknown time)")
max_tries = 100
- self.logInfo("Download limit reached, reconnect or wait %s" % time_str)
+ self.logInfo(_("Download limit reached, reconnect or wait %s") % time_str)
self.setWait(wait_time, True)
self.wait()
- self.retry(max_tries=max_tries, reason="Download limit reached")
+ self.retry(max_tries=max_tries, reason=_("Download limit reached"))
- def parseHtmlForm(self, attr_str='', input_names=None):
+
+ def parseHtmlForm(self, attr_str="", input_names={}):
return parseHtmlForm(attr_str, self.html, input_names)
+
def checkTrafficLeft(self):
- traffic = self.account.getAccountInfo(self.user, True)["trafficleft"]
- if traffic == -1:
+ traffic = self.account.getAccountInfo(self.user, True)['trafficleft']
+
+ if traffic is None:
+ return False
+ elif traffic == -1:
return True
- size = self.pyfile.size / 1024
- self.logInfo("Filesize: %i KiB, Traffic left for user %s: %i KiB" % (size, self.user, traffic))
- return size <= traffic
-
- # TODO: Remove in 0.5
- def wait(self, seconds=False, reconnect=False):
- if seconds:
- self.setWait(seconds, reconnect)
- super(SimpleHoster, self).wait()
+ else:
+ size = self.pyfile.size / 1024
+ self.logInfo(_("Filesize: %i KiB, Traffic left for user %s: %i KiB") % (size, self.user, traffic))
+ return size <= traffic
+
+
+ #@TODO: Remove in 0.4.10
+ def wait(self, seconds=0, reconnect=None):
+ return _wait(self, seconds, reconnect)
+
+
+ def error(self, reason="", type="parse"):
+ return _error(self, reason, type)