Saverr/svtplay-dl
1
0
Fork 0
mirror of https://github.com/spaam/svtplay-dl.git synced 2024-11-24 12:15:40 +01:00
Code Issues Projects Releases Wiki Activity

subtitle: catch http errors.

Browse Source
This commit is contained in:
Johan Andersson 2014-08-31 00:56:51 +02:00
parent e1e56773cb
commit 524fe2ce0c
1 changed files with 34 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
lib/svtplay_dl/subtitle/__init__.py
View File

@ -3,19 +3,30 @@ import json
import re import re
import os import os
from svtplay_dl.log import log from svtplay_dl.log import log
from svtplay_dl.utils import is_py2, is_py3, get_http_data from svtplay_dl.utils import is_py2, is_py3, get_http_data, HTTPError
class subtitle(object): class subtitle(object):
def __init__(self, url): def __init__(self, url):
self.url = url self.url = url
self.subtitle = None self.subtitle = None
def get_subdata(self):
if self.subtitle is None:
try:
self.subtitle = get_http_data(self.url)
except HTTPError:
return None
return self.subtitle
class subtitle_tt(subtitle): class subtitle_tt(subtitle):
def download(self, options): def download(self, options):
self.subtitle = get_http_data(self.url) subdata = self.get_subdata()
if subdata is None:
log.error("Can't download subtitle.")
return
i = 1 i = 1
data = "" data = ""
tree = ET.ElementTree(ET.fromstring(self.subtitle)) tree = ET.ElementTree(ET.fromstring(subdata))
xml = tree.find("{http://www.w3.org/2006/10/ttaf1}body").find("{http://www.w3.org/2006/10/ttaf1}div") xml = tree.find("{http://www.w3.org/2006/10/ttaf1}body").find("{http://www.w3.org/2006/10/ttaf1}div")
plist = list(xml.findall("{http://www.w3.org/2006/10/ttaf1}p")) plist = list(xml.findall("{http://www.w3.org/2006/10/ttaf1}p"))
for node in plist: for node in plist:
@ -44,8 +55,11 @@ class subtitle_tt(subtitle):
class subtitle_json(subtitle): class subtitle_json(subtitle):
def download(self, options): def download(self, options):
self.subtitle = get_http_data(self.url, cookiejar=options.cookiejar) subdata = self.get_subdata()
data = json.loads(self.subtitle) if subdata is None:
log.error("Can't download subtitle.")
return
data = json.loads(subdata)
number = 1 number = 1
subs = "" subs = ""
for i in data: for i in data:
@ -60,8 +74,11 @@ class subtitle_json(subtitle):
class subtitle_sami(subtitle): class subtitle_sami(subtitle):
def download(self, options): def download(self, options):
self.subtitle = get_http_data(self.url) subdata = self.get_subdata()
tree = ET.XML(self.subtitle) if subdata is None:
log.error("Can't download subtitle.")
return
tree = ET.XML(subdata)
subt = tree.find("Font") subt = tree.find("Font")
subs = "" subs = ""
n = 0 n = 0
@ -82,10 +99,13 @@ class subtitle_sami(subtitle):
class subtitle_smi(subtitle): class subtitle_smi(subtitle):
def download(self, options): def download(self, options):
self.subtitle = get_http_data(self.url) subdata = self.get_subdata()
if subdata is None:
log.error("Can't download subtitle.")
return
if is_py3: if is_py3:
self.subtitle = self.subtitle.decode("latin1") self.subtitle = self.subtitle.decode("latin1")
recomp = re.compile(r'<SYNC Start=(\d+)>(\r\n)?\s+<P Class=\w+>(.*)(<br>)?(\r\n)?\s+<SYNC Start=(\d+)>', re.U|re.M|re.I) recomp = re.compile(r'<SYNC Start=(\d+)>\s+<P Class=\w+>(.*)<br>\s+<SYNC Start=(\d+)>\s+<P Class=\w+>', re.M|re.I|re.U)
number = 1 number = 1
subs = "" subs = ""
TAG_RE = re.compile(r'<[^>]+>') TAG_RE = re.compile(r'<[^>]+>')
@ -103,11 +123,14 @@ class subtitle_smi(subtitle):
class subtitle_wsrt(subtitle): class subtitle_wsrt(subtitle):
def download(self, options): def download(self, options):
self.subtitle = get_http_data(self.url) subdata = self.get_subdata()
if subdata is None:
log.error("Can't download subtitle.")
return
recomp = re.compile(r"(\d+)\r\n([\d:\.]+ --> [\d:\.]+)?([^\r\n]+)?\r\n([^\r\n]+)\r\n(([^\r\n]*)\r\n)?") recomp = re.compile(r"(\d+)\r\n([\d:\.]+ --> [\d:\.]+)?([^\r\n]+)?\r\n([^\r\n]+)\r\n(([^\r\n]*)\r\n)?")
srt = "" srt = ""
subtract = False subtract = False
for i in recomp.finditer(self.subtitle): for i in recomp.finditer(subdata):
number = int(i.group(1)) number = int(i.group(1))
match = re.search(r'(\d+):(\d+):([\d\.]+) --> (\d+):(\d+):([\d\.]+)', i.group(2)) match = re.search(r'(\d+):(\d+):([\d\.]+) --> (\d+):(\d+):([\d\.]+)', i.group(2))
hour1 = int(match.group(1)) hour1 = int(match.group(1))