def download_subtitle(series_name, season, episode, output_dir):
"""
:param series_name:
:param season:
:param episode:
"""
dir_name = os.path.join(output_dir, "{}_s{:02}e{:02}".format(series_name, season, episode))
if not os.access(dir_name, os.F_OK):
os.makedirs(dir_name)
os.chdir(dir_name)
search_url = "{}{} s{:02}e{:02}".format(BASE_SEARCH, series_name, season, episode).replace(" ", "+")
logging.info("Search url: {}".format(search_url))
search_page_data = BeautifulSOAP(urllib2.urlopen(search_url).read())
# TODO handle zero matches
search_results_table = search_page_data.find(attrs={"class": "list first_column_title"})
results = search_results_table.tbody.findAll("tr")
results = [x for x in results if x.findAll("td")[2].a.div["alt"] == "English subtitles"]
results = [x.findAll("td")[0].findAll("div")[1].a["href"] for x in results]
for result in results:
download_page_url = BASE_URL + "/he/" + result
download_page_data = urllib2.urlopen(download_page_url).read()
download_button = BeautifulSOAP(download_page_data).find(attrs={"class": "button big download"})
download_url = BASE_URL + download_button.get("href")
download_data = urllib2.urlopen(download_url).read()
zip_filename = "output.zip"
open(zip_filename, "wb").write(download_data)
subprocess.call(["unzip", "-o", zip_filename])
logging.info("Unzipped {}".format(zip_filename))
os.unlink(zip_filename)
def addToMyChannels(cname):
try:
fileName=os.path.join(profile_path, 'MyChannels.xml')
print fileName
MyChannelList=getSoup(fileName,True)
except: MyChannelList=None
if not MyChannelList:
MyChannelList= BeautifulSOAP('<channels></channels>')
val=MyChannelList.find("channel",{"cname":cname})
#print 'val is ',val
if not val:
channeltag = Tag(MyChannelList, "channel")
channeltag['cname']=cname
MyChannelList.channels.insert(0, channeltag)
#print MyChannelList.prettify()
with open(fileName, "wb") as filewriter:
filewriter.write(str(MyChannelList))
class ExtractNewsInfo(object):
def __init__(self):
self.__soup = None
def parser(self , html):
self.clear()
self.__soup = BeautifulSOAP(html)
def get_tilte(self):
if self.__soup:
return self.__soup.html.head.title.text
raise NoDataParser("没有调用解析")
def __get_mata(self , name):
if self.__soup:
__keywords = self.__soup.find('meta' , attrs= {'name': name})
if __keywords:
return __keywords['content']
return None
def getChannelItems(name):
response = open(file, 'rb')
link=response.read()
soup = BeautifulSOAP(link, convertEntities=BeautifulStoneSoup.XML_ENTITIES)
channel_list = soup.find('channel', attrs={'name' : name})
items = channel_list('item')
for channel in channel_list('subchannel'):
name = channel('name')[0].string
thumb = channel('thumbnail')[0].string
addDir(name,'',3,thumb)
for item in items:
try:
name = item('title')[0].string
except:
pass
try:
if __settings__.getSetting('mirror_link') == "true":
try:
url = item('link')[1].string
except:
url = item('link')[0].string
if __settings__.getSetting('mirror_link_low') == "true":
try:
url = item('link')[2].string
except:
try:
url = item('link')[1].string
except:
url = item('link')[0].string
else:
url = item('link')[0].string
except:
pass
try:
thumbnail = item('thumbnail')[0].string
except:
thumbnail = ''
addLink(url,name,thumbnail)
def getChannelItems(name):
response = open(file, 'rb')
link = response.read()
soup = BeautifulSOAP(link, convertEntities=BeautifulStoneSoup.XML_ENTITIES)
channel_list = soup.find('channel', attrs={'name': name})
items = channel_list('item')
for channel in channel_list('subchannel'):
name = channel('name')[0].string
thumb = channel('thumbnail')[0].string
addDir(name, '', 3, thumb)
for item in items:
try:
name = item('title')[0].string
except:
pass
try:
if __settings__.getSetting('mirror_link') == "true":
try:
url = item('link')[1].string
except:
url = item('link')[0].string
if __settings__.getSetting('mirror_link_low') == "true":
try:
url = item('link')[2].string
except:
try:
url = item('link')[1].string
except:
url = item('link')[0].string
else:
url = item('link')[0].string
except:
pass
try:
thumbnail = item('thumbnail')[0].string
except:
thumbnail = ''
addLink(url, name, thumbnail)
def download_subtitle(series_name, season, episode, output_dir):
"""
:param series_name:
:param season:
:param episode:
"""
dir_name = os.path.join(
output_dir, "{}_s{:02}e{:02}".format(series_name, season, episode))
if not os.access(dir_name, os.F_OK):
os.makedirs(dir_name)
os.chdir(dir_name)
search_url = "{}{} s{:02}e{:02}".format(BASE_SEARCH, series_name, season,
episode).replace(" ", "+")
logging.info("Search url: {}".format(search_url))
search_page_data = BeautifulSOAP(urllib2.urlopen(search_url).read())
# TODO handle zero matches
search_results_table = search_page_data.find(
attrs={"class": "list first_column_title"})
results = search_results_table.tbody.findAll("tr")
results = [
x for x in results
if x.findAll("td")[2].a.div["alt"] == "English subtitles"
]
results = [x.findAll("td")[0].findAll("div")[1].a["href"] for x in results]
for result in results:
download_page_url = BASE_URL + "/he/" + result
download_page_data = urllib2.urlopen(download_page_url).read()
download_button = BeautifulSOAP(download_page_data).find(
attrs={"class": "button big download"})
download_url = BASE_URL + download_button.get("href")
download_data = urllib2.urlopen(download_url).read()
zip_filename = "output.zip"
open(zip_filename, "wb").write(download_data)
subprocess.call(["unzip", "-o", zip_filename])
logging.info("Unzipped {}".format(zip_filename))
os.unlink(zip_filename)
class ExtractNewsInfo(object):
def __init__(self):
self.__soup = None
def parser(self , html):
self.clear()
self.__soup = BeautifulSOAP(html)
def get_tilte(self):
if self.__soup:
return self.__soup.html.head.title.text
raise NoDataParser("没有调用解析")
def __get_mata(self , name):
if self.__soup:
__keywords = self.__soup.find('meta' , attrs= {'name': name})
if __keywords:
return __keywords['content']
return None
def get_key_words(self):
return self.__get_mata( 'keywords')
def get_description(self):
return self.__get_mata('description')
def clear(self):
if self.__soup:
self.__soup = None
