diff options
author | Walter Purcaro <vuolter@gmail.com> | 2014-10-23 15:47:27 +0200 |
---|---|---|
committer | Walter Purcaro <vuolter@gmail.com> | 2014-10-23 15:47:27 +0200 |
commit | 0a353e2f754370e70276bc0f3bad66deb2015607 (patch) | |
tree | d802658533ce71f6d14f05c7b427b71256137762 /module/plugins | |
parent | [Keep2shareCC] Fix handleCaptcha (diff) | |
download | pyload-0a353e2f754370e70276bc0f3bad66deb2015607.tar.xz |
[FilefactoryCom] Fix handleFree
Diffstat (limited to 'module/plugins')
-rw-r--r-- | module/plugins/hoster/FilefactoryCom.py | 75 |
1 files changed, 30 insertions, 45 deletions
diff --git a/module/plugins/hoster/FilefactoryCom.py b/module/plugins/hoster/FilefactoryCom.py index 0801ca9a1..dcb2fd8f0 100644 --- a/module/plugins/hoster/FilefactoryCom.py +++ b/module/plugins/hoster/FilefactoryCom.py @@ -2,6 +2,8 @@ import re +from urlparse import urljoin + from module.network.RequestFactory import getURL from module.plugins.internal.SimpleHoster import SimpleHoster, parseFileInfo @@ -10,9 +12,9 @@ def getInfo(urls): for url in urls: h = getURL(url, just_header=True) m = re.search(r'Location: (.+)\r\n', h) - if m and not re.match(m.group(1), FilefactoryCom.__pattern__): # It's a direct link! Skipping + if m and not re.match(m.group(1), FilefactoryCom.__pattern__): #: It's a direct link! Skipping yield (url, 0, 3, url) - else: # It's a standard html page + else: #: It's a standard html page file_info = parseFileInfo(FilefactoryCom, url, getURL(url)) yield file_info @@ -20,19 +22,23 @@ def getInfo(urls): class FilefactoryCom(SimpleHoster): __name__ = "FilefactoryCom" __type__ = "hoster" - __version__ = "0.51" + __version__ = "0.52" - __pattern__ = r'https?://(?:www\.)?filefactory\.com/file/(?P<id>\w+)' + __pattern__ = r'https?://(?:www\.)?filefactory\.com/(file|trafficshare/\w+)/\w+' __description__ = """Filefactory.com hoster plugin""" __license__ = "GPLv3" - __authors__ = [("stickell", "l.stickell@yahoo.it")] + __authors__ = [("stickell", "l.stickell@yahoo.it"), + ("Walter Purcaro", "vuolter@gmail.com")] FILE_INFO_PATTERN = r'<div id="file_name"[^>]*>\s*<h2>(?P<N>[^<]+)</h2>\s*<div id="file_info">\s*(?P<S>[\d.,]+) (?P<U>[\w^_]+) uploaded' - LINK_PATTERN = r'<a href="(https?://[^"]+)"[^>]*><i[^>]*></i> Download with FileFactory Premium</a>' OFFLINE_PATTERN = r'<h2>File Removed</h2>|This file is no longer available' - PREMIUM_ONLY_PATTERN = r'>Premium Account Required<' + + LINK_PATTERN = r'"([^"]+filefactory\.com/get.+?)"' + + WAIT_PATTERN = r'<div id="countdown_clock" data-delay="(\d+)">' + PREMIUM_ONLY_PATTERN = r'>Premium Account Required' COOKIES = [(".filefactory.com", "locale", "en_US.utf8")] @@ -43,55 +49,35 @@ class FilefactoryCom(SimpleHoster): elif "All free download slots on this server are currently in use" in self.html: self.retry(50, 15 * 60, "All free slots are busy") - m = re.search(r'data-href(?:-direct)?="(http://[^"]+)"', self.html) + m = re.search(self.LINK_PATTERN, self.html) + if m is None: + self.error("Free download link not found") + + dl_link = m.group(1) + + m = re.search(self.WAIT_PATTERN, self.html) if m: - t = re.search(r'<div id="countdown_clock" data-delay="(\d+)">', self.html) - if t: - t = t.group(1) - else: - self.logDebug("Unable to detect countdown duration. Guessing 60 seconds") - t = 60 - self.wait(t) - direct = m.group(1) - else: # This section could be completely useless now - # Load the page that contains the direct link - url = re.search(r"document\.location\.host \+\s*'(.+)';", self.html) - if url is None: - self.error('Unable to detect free link') - url = 'http://www.filefactory.com' + url.group(1) - self.html = self.load(url, decode=True) - - # Free downloads wait time - waittime = re.search(r'id="startWait" value="(\d+)"', self.html) - if not waittime: - self.error('Unable to detect wait time') - self.wait(int(waittime.group(1))) - - # Parse the direct link and download it - direct = re.search(r'data-href(?:-direct)?="(.*)" class="button', self.html) - if not direct: - self.error('Unable to detect free direct link') - direct = direct.group(1) - - self.logDebug("DIRECT LINK: " + direct) - self.download(direct, disposition=True) - - check = self.checkDownload({"multiple": "You are currently downloading too many files at once.", - "error": '<div id="errorMessage">'}) + self.wait(m.group(1)) + + self.download(dl_link, disposition=True) + + check = self.checkDownload({'multiple': "You are currently downloading too many files at once.", + 'error': '<div id="errorMessage">'}) if check == "multiple": self.logDebug("Parallel downloads detected; waiting 15 minutes") self.retry(wait_time=15 * 60, reason="Parallel downloads") elif check == "error": - self.fail("Unknown error") + self.error("Unknown error") def handlePremium(self): header = self.load(self.pyfile.url, just_header=True) + if 'location' in header: url = header['location'].strip() if not url.startswith("http://"): - url = "http://www.filefactory.com" + url + url = urljoin("http://www.filefactory.com", url) elif 'content-disposition' in header: url = self.pyfile.url else: @@ -101,7 +87,6 @@ class FilefactoryCom(SimpleHoster): if m: url = m.group(1) else: - self.error('Unable to detect premium direct link') + self.error("Premium download link not found") - self.logDebug("DIRECT PREMIUM LINK: " + url) self.download(url, disposition=True) |