nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

opensub logical id simplification

Browse source
This commit is contained in:
Julien Veyssier 2013-02-25 04:46:11 +01:00
commit 021be16558
2 changed files with 9 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

12
modules/opensubtitles/browser.py
View file

@ -51,12 +51,6 @@ class OpensubtitlesBrowser(BaseBrowser):
the id_file help to find the file into the page the id_file help to find the file into the page
if NO id_movie set, using id_file to form the URL if NO id_movie set, using id_file to form the URL
""" """
ids = id.split('|') self.location('http://www.opensubtitles.org/subtitles/%s' % id)
id_movie = ids[0] assert self.is_on_page(SubtitlePage)
id_file = ids[1] return self.page.get_subtitle()
if len(id_movie) > 0:
self.location('http://www.opensubtitles.org/search/sublanguageid-all/idmovie-%s' % id_movie)
else:
self.location('http://www.opensubtitles.org/subtitles/%s' % id_file)
assert self.is_on_page(SubtitlesPage) or self.is_on_page(SubtitlePage)
return self.page.get_subtitle(id_file)

27
modules/opensubtitles/pages.py
View file

@ -59,17 +59,6 @@ class SearchPage(BasePage):
class SubtitlesPage(BasePage): class SubtitlesPage(BasePage):
""" Page which contains several subtitles for a single movie """ Page which contains several subtitles for a single movie
""" """
def get_subtitle(self,id_file):
tabresults = self.parser.select(self.document.getroot(),'table#search_results')
if len(tabresults) > 0:
table = tabresults[0]
# for each result line, get informations
for line in self.parser.select(table,'tr'):
id_line = line.attrib.get('id','').replace('name','')
# TODO gerer le multi pages
if id_line.strip() == id_file.strip():
return self.get_subtitle_from_line(line)
def iter_subtitles(self): def iter_subtitles(self):
tabresults = self.parser.select(self.document.getroot(),'table#search_results') tabresults = self.parser.select(self.document.getroot(),'table#search_results')
if len(tabresults) > 0: if len(tabresults) > 0:
@ -81,7 +70,6 @@ class SubtitlesPage(BasePage):
yield self.get_subtitle_from_line(line) yield self.get_subtitle_from_line(line)
def get_subtitle_from_line(self,line): def get_subtitle_from_line(self,line):
id_movie = self.browser.geturl().split('idmovie-')[-1].split('/')[0]
cells = self.parser.select(line,'td') cells = self.parser.select(line,'td')
if len(cells) > 0: if len(cells) > 0:
first_cell = cells[0] first_cell = cells[0]
@ -106,9 +94,8 @@ class SubtitlesPage(BasePage):
cell_dl = cells[4] cell_dl = cells[4]
href = self.parser.select(cell_dl,'a',1).attrib.get('href','') href = self.parser.select(cell_dl,'a',1).attrib.get('href','')
url = "http://www.opensubtitles.org%s"%href url = "http://www.opensubtitles.org%s"%href
id_file = href.split('/')[-1] id = href.split('/')[-1]
id = "%s|%s"%(id_movie,id_file)
subtitle = Subtitle(id,name) subtitle = Subtitle(id,name)
subtitle.url = url subtitle.url = url
subtitle.fps = fps subtitle.fps = fps
@ -121,13 +108,11 @@ class SubtitlesPage(BasePage):
class SubtitlePage(BasePage): class SubtitlePage(BasePage):
""" Page which contains a single subtitle for a movie """ Page which contains a single subtitle for a movie
""" """
def get_subtitle(self,id): def get_subtitle(self):
father = self.parser.select(self.document.getroot(),'a#app_link',1).getparent() father = self.parser.select(self.document.getroot(),'a#app_link',1).getparent()
a = self.parser.select(father,'a')[1] a = self.parser.select(father,'a')[1]
id_file = a.attrib.get('href','').split('/')[-1] id = a.attrib.get('href','').split('/')[-1]
url = "http://www.opensubtitles.org/subtitleserve/sub/%s"%id_file url = "http://www.opensubtitles.org/subtitleserve/sub/%s"%id
id_movie = ""
sid = "%s|%s"%(id_movie,id_file)
link = self.parser.select(self.document.getroot(),'link[rel=bookmark]',1) link = self.parser.select(self.document.getroot(),'link[rel=bookmark]',1)
title = link.attrib.get('title','') title = link.attrib.get('title','')
nb_cd = int(title.lower().split('cd')[0].split()[-1]) nb_cd = int(title.lower().split('cd')[0].split()[-1])
@ -136,7 +121,7 @@ class SubtitlePage(BasePage):
name = title name = title
fps = 0 fps = 0
subtitle = Subtitle(sid,name) subtitle = Subtitle(id,name)
subtitle.url = url subtitle.url = url
subtitle.fps = fps subtitle.fps = fps
subtitle.language = lang subtitle.language = lang
@ -145,4 +130,4 @@ class SubtitlePage(BasePage):
return subtitle return subtitle
def iter_subtitles(self): def iter_subtitles(self):
yield self.get_subtitle(None) yield self.get_subtitle()