def downloadApk(self, avi, isBeta=False):
"""
downloadApk(apkInfo): Download the specified URL to APK file name
"""
apkname = '{0}-{1}.apk'.format(avi.name.replace('.beta', ''),
avi.realver.replace(' ', '_'))
logging.info('Downloading "{0}" from: {1}'.format(apkname,avi.download_src))
try:
if os.path.exists(apkname):
logging.info('Downloaded APK already exists.')
return
if os.path.exists(os.path.join('.', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ./apkcrawler/).')
return
if os.path.exists(os.path.join('..', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ../apkcrawler/).')
return
# Open the url
session = requests.Session()
session.proxies = Debug.getProxy()
r = session.get(avi.download_src,stream=True) #plazza blocks fetching it at one go, we need to stream it in chunks
with open(apkname, 'wb') as local_file:
for chunk in r.iter_content(1024):
local_file.write(chunk)
logging.debug(('beta:' if isBeta else 'reg :') + apkname)
return (('beta:' if isBeta else '' ) + apkname)
except OSError:
logging.exception('!!! Filename is not valid: "{0}"'.format(apkname))
def downloadApk(url,package,vercode):
"""
downloadApk(apkInfo): Download the specified URL to APK file name
"""
apkname = '{0}-{1}.apk'.format(package,
vercode)
logging.info('Downloading "{0}" from: {1}'.format(apkname,url))
try:
if os.path.exists(apkname):
logging.info('Downloaded APK already exists.')
return
if os.path.exists(os.path.join('.', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ./apkcrawler/).')
return
if os.path.exists(os.path.join('..', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ../apkcrawler/).')
return
# Open the url
session = requests.Session()
session.proxies = Debug.getProxy()
r = session.get(url,stream=True)
with open(apkname, 'wb') as local_file:
for chunk in r.iter_content(1024):
local_file.write(chunk)
print('{0} '.format(apkname)),
sys.stdout.flush()
except OSError:
logging.exception('!!! Filename is not valid: "{0}"'.format(apkname))
def downloadApk(url, package, vername, vercode, minSdk):
"""
downloadApk(apkInfo): Download the specified URL to APK file name
"""
apkname = "{0}_{1}-{2}_minAPI{3}.apk".format(package, vername.replace(" ", "_"), vercode, minSdk)
logging.info('Downloading "{0}" from: {1}'.format(apkname, url))
try:
if os.path.exists(apkname):
logging.info("Downloaded APK already exists.")
return
if os.path.exists(os.path.join(".", "apkcrawler", apkname)):
logging.info("Downloaded APK already exists (in ./apkcrawler/).")
return
if os.path.exists(os.path.join("..", "apkcrawler", apkname)):
logging.info("Downloaded APK already exists (in ../apkcrawler/).")
return
# Open the url
session = requests.Session()
session.proxies = Debug.getProxy()
r = session.get(url)
with open(apkname, "wb") as local_file:
local_file.write(r.content)
print("{0} ".format(apkname)),
sys.stdout.flush()
except OSError:
logging.exception('!!! Filename is not valid: "{0}"'.format(apkname))
def downloadApk(self, avi, isBeta=False):
"""
downloadApk(apkInfo): Download the specified URL to APK file name
"""
apkname = '{0}-{1}.apk'.format(avi.name.replace('.beta', ''),
avi.realver.replace(' ', '_'))
logging.info('Downloading "{0}" from: {1}'.format(apkname,avi.download_src))
try:
if os.path.exists(apkname):
logging.info('Downloaded APK already exists.')
return
if os.path.exists(os.path.join('.', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ./apkcrawler/).')
return
if os.path.exists(os.path.join('..', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ../apkcrawler/).')
return
# Open the url
session = requests.Session()
session.proxies = Debug.getProxy()
user_agent = {'User-agent': 'Mozilla/5.0'} #they don't like scripted downloads and then offer their own app instead
r = session.get(avi.download_src, headers = user_agent)
with open(apkname, 'wb') as local_file:
local_file.write(r.content)
logging.debug(('beta:' if isBeta else 'reg :') + apkname)
return (('beta:' if isBeta else '' ) + apkname)
except OSError:
logging.exception('!!! Filename is not valid: "{0}"'.format(apkname))
def downloadApk(url,package):
"""
downloadApk(apkInfo): Download the specified URL to APK file name
"""
apkname = '{0}.apk'.format(package)
logging.info('Downloading "{0}" from: {1}'.format(apkname,url))
try:
if os.path.exists(apkname):
logging.info('Downloaded APK already exists.')
return
if os.path.exists(os.path.join('.', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ./apkcrawler/).')
return
if os.path.exists(os.path.join('..', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ../apkcrawler/).')
return
# Open the url
session = requests.Session()
session.proxies = Debug.getProxy()
user_agent = {'User-agent': 'Mozilla/5.0'} #they don't like scripted downloads and then offer their own app instead
r = session.get(url, headers = user_agent)
with open(apkname, 'wb') as local_file:
local_file.write(r.content)
print('{0} '.format(apkname)),
sys.stdout.flush()
except OSError:
logging.exception('!!! Filename is not valid: "{0}"'.format(apkname))
def checkOneApp(self, apkid):
"""
checkOneApp(apkid):
"""
logging.info('Checking app: {0}'.format(apkid))
url = 'http://apk-dl.com/' + apkid
session = requests.Session()
session.proxies = Debug.getProxy()
logging.debug('Requesting: ' + url)
resp = session.get(url)
html = unicodedata.normalize('NFKD', resp.text).encode('ascii', 'ignore')
try:
dom = BeautifulSoup(html, 'html5lib')
apklist = dom.findAll('ul', {'class': 'apks dlist'})[0]
apks = apklist.findAll('div', {'class': 'details'})
for apk in apks:
items = apk.findAll('div')
dApk = {}
for item in items:
itext = '{0}'.format(item.get_text().encode('ascii', 'ignore'))
itext = re.sub('\s', '', itext)
itextsp = itext.split(':', 1)
if len(itextsp) == 2:
dApk[str(itextsp[0])] = str(itextsp[1])
apkurl = apk.find('a', {'class': 'btn btn-success'})
if apkurl:
dApk['url'] = 'http:' + apkurl['href']
Debug.printDictionary(dApk)
if 'Version' in dApk and 'RequiresAndroid' in dApk:
(trash, sdk) = dApk['RequiresAndroid'].split('API:', 1)
sdk = sdk[0:-1]
(ver, vercode) = dApk['Version'].split('(Code:', 1)
ver = ver.split('(', 1)[0].strip()
vercode = vercode[0:-1].strip()
avi = ApkVersionInfo(name=apkid,
sdk=sdk,
ver=ver,
vercode=vercode,
download_src = dApk['url']
)
if self.report.isThisApkNeeded(avi):
return self.downloadApk(avi)
except IndexError:
logging.info('{0} not supported by apk-dl.com ...'.format(apkid))
except:
logging.exception('!!! Error parsing html from: "{0}"'.format(url))
def checkOneApp(self, apkid):
"""
checkOneApp(apkid):
"""
logging.info('Checking app: {0}'.format(apkid))
avis = []
filenames = []
try:
upToDownName = allUpToDownNames[apkid]
appurl = 'http://' + upToDownName + '.en.uptodown.com/android/old'
session = requests.Session()
session.proxies = Debug.getProxy()
logging.debug('Requesting: ' + appurl)
try:
appresp = session.get(appurl)
apphtml = unicodedata.normalize('NFKD', appresp.text).encode('ascii', 'ignore')
appdom = BeautifulSoup(apphtml, 'html5lib')
latestver = appdom.find('span', {'itemprop': 'softwareVersion'})
if latestver: # sometimes there is only 1 version and no old versions, and you get the latest-version page of the app instead of the overview of old versions
avis.append(ApkVersionInfo(name=apkid,
ver=(latestver.contents[0].lstrip('v').strip().encode("ascii") if latestver.contents else ''), # sometimes there is no versionnumber, or they set a v in front of the versionName; it presents unicode for some reason
scrape_src='http://' + upToDownName + '.en.uptodown.com/android/download'))
else:
appversions = appdom.findAll('section', {'class': 'container'})
for apk in appversions[0:5]: # limit ourself to only the first 5 results; the chance that there are updates beyond that point is smaller than the chance of having errors in the versionname
apkurl = apk.find('a')['href']
apkver = apk.find('span', {'class': 'app_card_version'}).contents
avis.append(ApkVersionInfo(name=apkid,
ver=(apkver[0].lstrip('v').strip().encode("ascii") if apkver else ''), # sometimes there is no versionnumber, or they set a v in front of the versionName; it presents unicode for some reason
scrape_src=apkurl))
# END: for appversions
# END: if lastestver
for avi in avis:
if self.report.isThisApkNeeded(avi):
logging.debug('Requesting: ' + avi.scrape_src)
try:
downloadresp = session.get(avi.scrape_src)
downloadhtml = unicodedata.normalize('NFKD', downloadresp.text).encode('ascii', 'ignore')
downloaddom = BeautifulSoup(downloadhtml, 'html5lib')
avi.download_src = downloaddom.find('iframe', {'id': 'iframe_download'})['src'] #note that this url will still result in a redirect 302
filenames.append(self.downloadApk(avi))
except:
logging.exception('!!! Error parsing html from: "{0}"'.format(avi.scrape_src))
# END: if isThisApkNeeded
# END: for avis
except:
logging.exception('!!! Error parsing html from: "{0}"'.format(appurl))
except KeyError:
logging.info('{0} not in uptodown.com dictionary'.format(apkid))
return filenames
def downloadApk(apkInfo):
"""
downloadApk(apkInfo): Download the specified URL to APK file name
"""
url = apkInfo['path']
cpu = apkInfo.get('cpu', '')
if cpu != '':
cpu = '({0})'.format(cpu)
dpi = apkInfo.get('screenCompat', '(nodpi)')
if dpi != '(nodpi)':
dpi = '({0}dpi)'.format(doDpiStuff(dpi, ','))
apkname = '{0}_{1}-{2}_minAPI{3}{4}{5}.apk'.format(apkInfo['package'],
apkInfo['vername'].replace(' ', '_'),
apkInfo['vercode'],
apkInfo['minSdk'],
cpu, dpi)
logging.info('Downloading "{0}" from: {1}'.format(apkname,url))
try:
if os.path.exists(apkname):
logging.info('Downloaded APK already exists.')
return
if os.path.exists(os.path.join('.', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ./apkcrawler/).')
return
if os.path.exists(os.path.join('..', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ../apkcrawler/).')
return
# Open the url
session = requests.Session()
session.proxies = Debug.getProxy()
r = session.get(url)
with open(apkname, 'wb') as local_file:
local_file.write(r.content)
print('{0} '.format(apkname)),
sys.stdout.flush()
except OSError:
logging.exception('!!! Filename is not valid: "{0}"'.format(apkname))
def checkOneApp(apkid):
"""
checkOneApp(apkid):
"""
dAllApks = Global.dAllApks
maxVerEachApk = Global.maxVerEachApk
minSdkEachApk = Global.minSdkEachApk
logging.info('Checking app: {0}'.format(apkid))
html_name = '{0}.html'.format(apkid)
url = 'http://www.plazza.ir/app/' + apkid + '?hl=en'
html = Debug.readFromFile(html_name)
if html == '':
session = requests.Session()
session.proxies = Debug.getProxy()
logging.debug('Requesting: ' + url)
resp = session.get(url)
html = unicodedata.normalize('NFKD', resp.text).encode('ascii', 'ignore')
Debug.writeToFile(html_name, html, resp.encoding)
try:
dom = BeautifulSoup(html, 'html5lib')
latestapk = dom.findAll('a', {'itemprop': 'downloadUrl'})[0]
appid = re.search('(^\/dl\/)([0-9]+)(\/1$)', latestapk['href']).group(2)
latesturl = session.head('http://www.plazza.ir' + latestapk['href'],allow_redirects=True).url
latestver = re.search('(_)([0-9]+)(\.apk)$', latesturl).group(2)
#We still miss versioncode comparison here
downloadApk(latesturl,apkid,latestver)
#Fetching of older versions is not completed, because it requires VIP accounts
#olderapks = dom.findAll('div', {'style': 'direction: rtl'})[0].findAll('a', {'target': '_blank'})
#for apk in olderapks:
# apkver = re.search('(\/)([0-9]+)(\?.*$|$)', apk['href']).group(2) #number is either end of string or there can be an ? for extra GET parameters
# apkurl = session.head('http://www.plazza.ir/dl_version/' + appid + '/' + apkver + '/1',allow_redirects=True).url
except AttributeError:
logging.info('{0} has an invalid version in the download URL ...'.format(apkid))
except IndexError:
logging.info('{0} not supported by plazza.ir ...'.format(apkid))
except:
logging.exception('!!! Error parsing html from: "{0}"'.format(url))
def checkOneApp(self, apkid):
"""
checkOneApp(apkid):
"""
logging.info('Checking app: {0}'.format(apkid))
url = 'http://www.plazza.ir/app/' + apkid + '?hl=en'
session = requests.Session()
session.proxies = Debug.getProxy()
logging.debug('Requesting: ' + url)
try:
resp = session.get(url,allow_redirects=False) #we get a 302 if application is not found
if resp.status_code == httplib.OK:
html = unicodedata.normalize('NFKD', resp.text).encode('ascii', 'ignore')
try:
dom = BeautifulSoup(html, 'html5lib')
latesthref = dom.find('a', {'itemprop': 'downloadUrl'})['href']
latestver = dom.find('div', {'itemprop': 'softwareVersion'}).contents[0].strip()
appid = re.search('(^\/dl\/)([0-9]+)(\/1$)', latesthref).group(2)
latesturl = session.head('http://www.plazza.ir' + latesthref,allow_redirects=True).url
#latestvercode = re.search('(_)([0-9]+)(\.apk)$', latesturl).group(2) #apparently this is NOT a (reliable?) versioncode
avi = ApkVersionInfo(name=apkid,
ver=latestver,
#vercode=latestvercode,
download_src=latesturl
)
if self.report.isThisApkNeeded(avi):
return self.downloadApk(avi)
#Fetching of older versions is not completed, because it requires VIP accounts
#olderapks = dom.find('div', {'style': 'direction: rtl'}).findAll('a', {'target': '_blank'})
#for apk in olderapks:
# apkver = re.search('(\/)([0-9]+)(\?.*$|$)', apk['href']).group(2) #number is either end of string or there can be an ? for extra GET parameters
# apkurl = session.head('http://www.plazza.ir/dl_version/' + appid + '/' + apkver + '/1',allow_redirects=True).url
except:
logging.exception('!!! Error parsing html from: "{0}"'.format(url))
else:
logging.info('{0} not available on plazza.ir'.format(apkid))
except:
logging.exception('Connection error to plazza.ir when checking {0} at {1}'.format(apkid,url))
def getUrlFromRedirect(self, apkname, url):
"""
getUrlFromRedirect(url):
"""
link = ''
session = requests.Session()
session.proxies = Debug.getProxy()
logging.debug('Requesting2: ' + url)
resp = session.get(url)
html = unicodedata.normalize('NFKD', resp.text).encode('ascii', 'ignore')
try:
dom = BeautifulSoup(html, 'html5lib')
link = dom.find('span', {'class': 'glyphicon glyphicon-cloud-download'}).parent['href']
except:
logging.exception('!!! Error parsing html from: "{0}"'.format(url))
return link
def downloadApk(self, apkInfo, isBeta=False):
"""
downloadApk(apkInfo): Download the specified URL to APK file name
"""
apkname = '{0}_{1}-{2}_minAPI{3}.apk'.format(apkInfo.name,
apkInfo.ver,
apkInfo.vercode,
apkInfo.sdk)
url = self.getUrlFromRedirect(apkname, apkInfo.download_src)
if url == '':
logging.error('Unable to determine redirect url for ' + apkname)
return
logging.info('Downloading "{0}" from: {1}'.format(apkname,url))
try:
if os.path.exists(apkname):
logging.info('Downloaded APK already exists.')
return
if os.path.exists(os.path.join('.', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ./apkcrawler/).')
return
if os.path.exists(os.path.join('..', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ../apkcrawler/).')
return
# Open the url
session = requests.Session()
session.proxies = Debug.getProxy()
r = session.get(url)
with open(apkname, 'wb') as local_file:
local_file.write(r.content)
logging.debug(('beta:' if isBeta else 'reg :') + apkname)
return (('beta:' if isBeta else '' ) + apkname)
except OSError:
logging.exception('!!! Filename is not valid: "{0}"'.format(apkname))
def checkOneApp(apkid):
"""
checkOneApp(apkid):
"""
dAllApks = Global.dAllApks
maxVerEachApk = Global.maxVerEachApk
minSdkEachApk = Global.minSdkEachApk
logging.info('Checking app: {0}'.format(apkid))
try:
upToDownName = allUpToDownNames[apkid]
html_name = '{0}.html'.format(upToDownName)
url = 'http://' + upToDownName + '.en.uptodown.com/android/download'
html = Debug.readFromFile(html_name)
if html == '':
session = requests.Session()
session.proxies = Debug.getProxy()
logging.debug('Requesting: ' + url)
resp = session.get(url)
html = unicodedata.normalize('NFKD', resp.text).encode('ascii', 'ignore')
Debug.writeToFile(html_name, html, resp.encoding)
try:
dom = BeautifulSoup(html, 'html5lib')
latestapk = dom.findAll('iframe', {'id': 'iframe_download'})[0]['src'] #note that this url will still result in a redirect 302
#We still miss versioncode comparison here
downloadApk(latestapk,apkid)
#We still miss fetching older versions
except IndexError:
logging.info('{0} not supported by uptodown.com ...'.format(apkid))
except:
logging.exception('!!! Error parsing html from: "{0}"'.format(url))
except KeyError:
logging.info('{0} not in uptodown.com dictionary...'.format(apkid))
def getUrlFromRedirect(apkname, url):
"""
getUrlFromRedirect(url):
"""
html_name = '{0}_redirect.html'.format(apkname)
html = Debug.readFromFile(html_name)
link = ''
if html == '':
session = requests.Session()
session.proxies = Debug.getProxy()
logging.debug('Requesting2: ' + url)
resp = session.get(url)
html = unicodedata.normalize('NFKD', resp.text).encode('ascii', 'ignore')
Debug.writeToFile(html_name, html, resp.encoding)
try:
dom = BeautifulSoup(html, 'html5lib')
link = dom.findAll('span', {'class': 'glyphicon glyphicon-cloud-download'})[0].parent['href']
except:
logging.exception('!!! Error parsing html from: "{0}"'.format(url))
return link
def downloadApk(self, avi, isBeta=False):
"""
downloadApk(apkInfo): Download the specified URL to APK file name
"""
apkname = '{0}_{1}-{2}_minAPI{3}.apk'.format(avi.name.replace('.beta', ''),
avi.realver.replace(' ', '_'),
avi.vercode,
avi.sdk)
logging.info('Downloading "{0}" from: {1}'.format(apkname,avi.download_src))
try:
if os.path.exists(apkname):
logging.info('Downloaded APK already exists.')
return
if os.path.exists(os.path.join('.', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ./apkcrawler/).')
return
if os.path.exists(os.path.join('..', 'apkcrawler', apkname)):
logging.info('Downloaded APK already exists (in ../apkcrawler/).')
return
# Open the url
session = requests.Session()
session.proxies = Debug.getProxy()
r = session.get(avi.download_src)
with open(apkname, 'wb') as local_file:
local_file.write(r.content)
logging.debug(('beta:' if isBeta else 'reg :') + apkname)
return (('beta:' if isBeta else '' ) + apkname)
except OSError:
logging.exception('!!! Filename is not valid: "{0}"'.format(apkname))
def checkOneApp(apkid):
"""
checkOneApp(apkid):
"""
dAllApks = Global.dAllApks
maxVerEachApk = Global.maxVerEachApk
minSdkEachApk = Global.minSdkEachApk
logging.info('Checking app: {0}'.format(apkid))
html_name = '{0}.html'.format(apkid)
url = 'http://apk-dl.com/' + apkid
html = Debug.readFromFile(html_name)
if html == '':
session = requests.Session()
session.proxies = Debug.getProxy()
logging.debug('Requesting: ' + url)
resp = session.get(url)
html = unicodedata.normalize('NFKD', resp.text).encode('ascii', 'ignore')
Debug.writeToFile(html_name, html, resp.encoding)
try:
dom = BeautifulSoup(html, 'html5lib')
apklist = dom.findAll('ul', {'class': 'apks dlist'})[0]
apks = apklist.findAll('div', {'class': 'details'})
maxApkInfo = ApkVersionInfo(name=apkid, ver=maxVerEachApk[apkid])
for apk in apks:
items = apk.findAll('div')
dApk = {}
for item in items:
itext = '{0}'.format(item.get_text().encode('ascii', 'ignore'))
itext = re.sub('\s', '', itext)
itextsp = itext.split(':', 1)
if len(itextsp) == 2:
dApk[str(itextsp[0])] = str(itextsp[1])
dApk['url'] = 'http:' + apk.find('a', {'class': 'btn btn-success'})['href']
Debug.printDictionary(dApk)
if 'Version' in dApk and 'RequiresAndroid' in dApk:
(trash, sdk) = dApk['RequiresAndroid'].split('API:', 1)
sdk = sdk[0:-1]
(ver, vercode) = dApk['Version'].split('(Code:', 1)
ver = ver.split('(', 1)[0]
vercode = vercode[0:-1]
tmpApkInfo = ApkVersionInfo(name=apkid, sdk=sdk, ver=ver, vercode=vercode)
tmpApkInfo.download_url = dApk['url']
if maxApkInfo <= tmpApkInfo:
thisSdk = int(tmpApkInfo.sdk)
if thisSdk < minSdkEachApk[apkid]:
logging.debug('SdkTooLow: {0}({1})'.format(apkid, thisSdk))
continue
if not filter(lambda apk: apk.vercode == tmpApkInfo.vercode, dAllApks[apkid]):
logging.debug(tmpApkInfo.fullString(maxVerEachApk[apkid]))
downloadApk(tmpApkInfo)
except IndexError:
logging.info('{0} not supported by apk-dl.com ...'.format(apkid))
except:
logging.exception('!!! Error parsing html from: "{0}"'.format(url))
