def iter_subtitles(self, language):
linksresults = self.parser.select(self.document.getroot(), "a.subtitle_page_link")
for link in linksresults:
id = unicode(link.attrib.get("href", "").split("-p")[-1])
name = unicode(link.text_content())
tr = link.getparent().getparent().getparent()
cdtd = self.parser.select(tr, "td")[4]
nb_cd = int(cdtd.text)
description = NotLoaded
subtitle = Subtitle(id, name)
subtitle.nb_cd = nb_cd
subtitle.language = language
subtitle.description = description
yield subtitle
def iter_subtitles(self, language):
linksresults = self.parser.select(self.document.getroot(), 'a.subtitle_page_link')
for link in linksresults:
id = unicode(link.attrib.get('href', '').split('-p')[-1])
name = unicode(link.text_content())
tr = link.getparent().getparent().getparent()
cdtd = self.parser.select(tr, 'td')[4]
nb_cd = int(cdtd.text)
description = NotLoaded
subtitle = Subtitle(id, name)
subtitle.nb_cd = nb_cd
subtitle.language = language
subtitle.description = description
yield subtitle
def iter_subtitles(self):
season = ''
series_name = CleanText('//div[has-class("msg")]//h1//span[@itemprop="name"]')(self.doc)
# A regexp to recover the sub id from url
regexp = re.compile('.*/imdbid-(?P<episode_id>\d+)$')
for sub in self.doc.xpath('//table[@id="search_results"]//tbody//tr[not(contains(@class,"head"))]'):
if not Attr('.', 'class', default=None)(sub):
season = CleanText('.//td[1]')(sub)
else:
subtitle = Subtitle()
episode = CleanText('.//td[1]')(sub)
subtitle.name = '%s - %s - Episode %s' % (series_name, season, episode)
url = Link('.//td[3]//a')(sub)
subtitle.url = self.browser.absurl(url)
result = regexp.match(url)
subtitle.id = result.groupdict()['episode_id']
yield subtitle
def get_subtitle(self, id):
href = id.split('|')[1]
# we have to find the 'tr' which contains the link to this address
a = self.parser.select(self.document.getroot(), 'a[href="%s"]' % href,
1)
line = a.getparent().getparent().getparent().getparent().getparent()
cols = self.parser.select(line, 'td')
traduced_title = self.parser.select(cols[0], 'font', 1).text.lower()
original_title = self.parser.select(cols[1], 'font', 1).text.lower()
nb_cd = self.parser.select(cols[2], 'font', 1).text.strip()
nb_cd = int(nb_cd.split()[0])
traduced_title_words = traduced_title.split()
original_title_words = original_title.split()
# this is to trash special spacing chars
traduced_title = " ".join(traduced_title_words)
original_title = " ".join(original_title_words)
name = unicode('%s (%s)' % (original_title, traduced_title))
url = unicode('http://davidbillemont3.free.fr/%s' % href)
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.ext = url.split('.')[-1]
subtitle.language = unicode('fr')
subtitle.nb_cd = nb_cd
subtitle.description = NotAvailable
return subtitle
def get_subtitle(self):
filename_line = self.doc.xpath('//img[@alt="filename"]')[0].getparent().getparent()
name = to_unicode(filename_line.xpath('.//td')[2].text)
id = self.url.split('/')[-1].replace('.html', '').replace('subtitle-', '')
url = '%s/download-%s.html' % (self.browser.BASEURL, id)
amount_line, = self.doc.xpath('//tr[contains(@title, "amount")]')
nb_cd = int(amount_line.xpath('.//td')[2].text)
lang = url.split('-')[-1].split('.html')[0]
filenames_line, = self.doc.xpath('//tr[contains(@title,"list")]')
file_names = filenames_line.xpath('.//td')[2].text_content().strip().replace('.srt', '.srt\n')
desc = u"files :\n"
desc += file_names
m = re.match('(.*?)\.(\w+)$', name)
if m:
name = m.group(1)
ext = m.group(2)
else:
ext = 'zip'
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.ext = ext
subtitle.language = lang
subtitle.nb_cd = nb_cd
subtitle.description = desc
return subtitle
def get_subtitle(self):
filename_line = self.parser.select(self.document.getroot(),
'img[alt=filename]',
1).getparent().getparent()
name = unicode(self.parser.select(filename_line, 'td')[2].text)
id = self.browser.geturl().split('/')[-1].replace('.html', '').replace(
'subtitle-', '')
url = unicode('http://%s/download-%s.html' % (self.browser.DOMAIN, id))
amount_line = self.parser.select(self.document.getroot(),
'tr[title~=amount]', 1)
nb_cd = int(self.parser.select(amount_line, 'td')[2].text)
lang = unicode(url.split('-')[-1].split('.html')[0])
filenames_line = self.parser.select(self.document.getroot(),
'tr[title~=list]', 1)
file_names = self.parser.select(
filenames_line,
'td')[2].text_content().strip().replace('.srt', '.srt\n')
desc = u"files :\n"
desc += file_names
m = re.match('(.*?)\.(\w+)$', name)
if m:
name = m.group(1)
ext = m.group(2)
else:
ext = 'zip'
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.ext = ext
subtitle.language = lang
subtitle.nb_cd = nb_cd
subtitle.description = desc
return subtitle
def iter_subtitles(self):
season = ''
series_name = CleanText(
'//div[has-class("msg")]//h1//span[@itemprop="name"]')(self.doc)
# A regexp to recover the sub id from url
regexp = re.compile('.*/imdbid-(?P<episode_id>\d+)$')
for sub in self.doc.xpath(
'//table[@id="search_results"]//tbody//tr[not(contains(@class,"head"))]'
):
if not Attr('.', 'class', default=None)(sub):
season = CleanText('.//td[1]')(sub)
else:
subtitle = Subtitle()
episode = CleanText('.//td[1]')(sub)
subtitle.name = '%s - %s - Episode %s' % (series_name, season,
episode)
url = Link('.//td[3]//a')(sub)
subtitle.url = self.browser.absurl(url)
result = regexp.match(url)
subtitle.id = result.groupdict()['episode_id']
yield subtitle
def get_subtitle(self, id):
href = id.split('|')[1]
# we have to find the 'tr' which contains the link to this address
a = self.parser.select(self.document.getroot(), 'a[href="%s"]' % href, 1)
line = a.getparent().getparent().getparent().getparent().getparent()
cols = self.parser.select(line, 'td')
traduced_title = self.parser.select(cols[0], 'font', 1).text.lower()
original_title = self.parser.select(cols[1], 'font', 1).text.lower()
nb_cd = self.parser.select(cols[2], 'font', 1).text.strip()
nb_cd = int(nb_cd.split()[0])
traduced_title_words = traduced_title.split()
original_title_words = original_title.split()
# this is to trash special spacing chars
traduced_title = " ".join(traduced_title_words)
original_title = " ".join(original_title_words)
name = unicode('%s (%s)' % (original_title, traduced_title))
url = unicode('http://davidbillemont3.free.fr/%s' % href)
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.ext = url.split('.')[-1]
subtitle.language = unicode('fr')
subtitle.nb_cd = nb_cd
subtitle.description = NotAvailable
return subtitle
def get_subtitle(self):
desc = NotAvailable
a = self.parser.select(self.document.getroot(), 'a#bt-dwl', 1)
id = a.attrib.get('rel', '').split('/')[-1]
m = re.match('Download \((\w+)\)', self.parser.tocleanstring(a))
if m:
ext = m.group(1)
else:
ext = u'zip'
url = unicode('http://www.opensubtitles.org/subtitleserve/sub/%s' % id)
link = self.parser.select(self.document.getroot(), 'link[rel=bookmark]', 1)
title = unicode(link.attrib.get('title', ''))
nb_cd = int(title.lower().split('cd')[0].split()[-1])
lang = unicode(title.split('(')[1].split(')')[0])
file_names = self.parser.select(self.document.getroot(), "img[title~=filename]")
if len(file_names) > 0:
file_name = file_names[0].getparent().text_content()
file_name = ' '.join(file_name.split())
desc = u'files :'
for f in file_names:
desc_line = f.getparent().text_content()
desc += '\n'+' '.join(desc_line.split())
name = unicode('%s (%s)' % (title, file_name))
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.ext = ext
for lshort, llong in LANGUAGE_CONV.items():
if lang == llong:
lang = unicode(lshort)
break
subtitle.language = lang
subtitle.nb_cd = nb_cd
subtitle.description = desc
return subtitle
def get_subtitle(self):
filename_line = self.parser.select(self.document.getroot(), 'img[alt=filename]', 1).getparent().getparent()
name = unicode(self.parser.select(filename_line, 'td')[2].text)
id = self.browser.geturl().split('/')[-1].replace('.html', '').replace('subtitle-', '')
url = unicode('http://%s/download-%s.html' % (self.browser.DOMAIN, id))
amount_line = self.parser.select(self.document.getroot(), 'tr[title~=amount]', 1)
nb_cd = int(self.parser.select(amount_line, 'td')[2].text)
lang = unicode(url.split('-')[-1].split('.html')[0])
filenames_line = self.parser.select(self.document.getroot(), 'tr[title~=list]', 1)
file_names = self.parser.select(filenames_line, 'td')[2].text_content().strip().replace('.srt', '.srt\n')
desc = u"files :\n"
desc += file_names
m = re.match('(.*?)\.(\w+)$', name)
if m:
name = m.group(1)
ext = m.group(2)
else:
ext = 'zip'
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.ext = ext
subtitle.language = lang
subtitle.nb_cd = nb_cd
subtitle.description = desc
return subtitle
def get_subtitle(self, id):
language = NotAvailable
url = NotAvailable
nb_cd = NotAvailable
links_info = self.parser.select(self.document.getroot(), "fieldset.information a")
for link in links_info:
href = link.attrib.get("href", "")
if "/fr/ppodnapisi/kategorija/jezik/" in href:
nlang = href.split("/")[-1]
for lang, langnum in LANGUAGE_NUMBERS.items():
if str(langnum) == str(nlang):
language = unicode(lang)
break
desc = u""
infos = self.parser.select(self.document.getroot(), "fieldset.information")
for info in infos:
for p in self.parser.select(info, "p"):
desc += "%s\n" % (u" ".join(p.text_content().strip().split()))
spans = self.parser.select(info, "span")
for span in spans:
if span.text is not None and "CD" in span.text:
nb_cd = int(self.parser.select(span.getparent(), "span")[1].text)
title = unicode(self.parser.select(self.document.getroot(), "head title", 1).text)
name = title.split(" - ")[0]
dllinks = self.parser.select(self.document.getroot(), "div.footer > a.download")
for link in dllinks:
href = link.attrib.get("href", "")
if id in href:
url = u"http://www.podnapisi.net%s" % href
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.language = language
subtitle.nb_cd = nb_cd
subtitle.description = desc
return subtitle
def get_subtitle(self, id):
language = NotAvailable
url = NotAvailable
nb_cd = NotAvailable
links_info = self.parser.select(self.document.getroot(), 'fieldset.information a')
for link in links_info:
href = link.attrib.get('href', '')
if '/fr/ppodnapisi/kategorija/jezik/' in href:
nlang = href.split('/')[-1]
for lang, langnum in LANGUAGE_NUMBERS.items():
if str(langnum) == str(nlang):
language = unicode(lang)
break
desc = u''
infos = self.parser.select(self.document.getroot(), 'fieldset.information')
for info in infos:
for p in self.parser.select(info, 'p'):
desc += '%s\n' % (u' '.join(p.text_content().strip().split()))
spans = self.parser.select(info, 'span')
for span in spans:
if span.text is not None and 'CD' in span.text:
nb_cd = int(self.parser.select(span.getparent(), 'span')[1].text)
title = unicode(self.parser.select(self.document.getroot(), 'head title', 1).text)
name = title.split(' - ')[0]
dllinks = self.parser.select(self.document.getroot(), 'div.footer > a.download')
for link in dllinks:
href = link.attrib.get('href', '')
if id in href:
url = u'http://www.podnapisi.net%s' % href
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.language = language
subtitle.nb_cd = nb_cd
subtitle.description = desc
return subtitle
def get_subtitle_from_line(self, line):
cells = self.parser.select(line, 'td')
if len(cells) > 0:
links = self.parser.select(line, 'a')
a = links[0]
name = u" ".join(a.text.strip().split())
first_cell = cells[0]
spanlist = self.parser.select(first_cell, 'span')
if len(spanlist) > 0:
long_name = spanlist[0].attrib.get('title', '')
else:
texts = first_cell.itertext()
long_name = texts.next()
long_name = texts.next()
if "Download at 25" in long_name:
long_name = "---"
name = "%s (%s)" % (name, long_name)
second_cell = cells[1]
link = self.parser.select(second_cell, 'a', 1)
lang = link.attrib.get('href', '').split('/')[-1].split('-')[-1]
for lshort, llong in LANGUAGE_CONV.items():
if lang == llong:
lang = unicode(lshort)
break
nb_cd = int(cells[2].text.strip().lower().replace('cd', ''))
cell_dl = cells[4]
href = self.parser.select(cell_dl, 'a', 1).attrib.get('href', '')
url = unicode('http://www.opensubtitles.org%s' % href)
id = href.split('/')[-1]
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.language = lang
subtitle.nb_cd = nb_cd
subtitle.description = NotLoaded
return subtitle
def iter_subtitles(self, language, pattern):
pattern = pattern.strip().replace('+', ' ').lower()
pattern_words = pattern.split()
tab = self.parser.select(self.document.getroot(),
'table[bordercolor="#B8C0B2"]')
if len(tab) == 0:
tab = self.parser.select(self.document.getroot(),
'table[bordercolordark="#B8C0B2"]')
if len(tab) == 0:
return
# some results of freefind point on useless pages
if tab[0].attrib.get('width', '') != '100%':
return
for line in tab[0].getiterator('tr'):
cols = self.parser.select(line, 'td')
traduced_title = self.parser.select(cols[0], 'font',
1).text.lower()
original_title = self.parser.select(cols[1], 'font',
1).text.lower()
traduced_title_words = traduced_title.split()
original_title_words = original_title.split()
# if the pattern is one word and in the title OR if the
# intersection between pattern and the title is at least 2 words
if (len(pattern_words) == 1 and pattern in traduced_title_words) or\
(len(pattern_words) == 1 and pattern in original_title_words) or\
(len(list(set(pattern_words) & set(traduced_title_words))) > 1) or\
(len(list(set(pattern_words) & set(original_title_words))) > 1):
# this is to trash special spacing chars
traduced_title = " ".join(traduced_title_words)
original_title = " ".join(original_title_words)
nb_cd = self.parser.select(cols[2], 'font', 1).text.strip()
nb_cd = int(nb_cd.strip(' CD'))
name = unicode('%s (%s)' % (original_title, traduced_title))
href = self.parser.select(cols[3], 'a',
1).attrib.get('href', '')
url = unicode('http://davidbillemont3.free.fr/%s' % href)
id = unicode('%s|%s' %
(self.browser.geturl().split('/')[-1], href))
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.ext = url.split('.')[-1]
subtitle.language = unicode('fr')
subtitle.nb_cd = nb_cd
subtitle.description = NotAvailable
yield subtitle
def get_subtitle(self, id=None):
subtitle = Subtitle()
subtitle.description = CleanText(
'.//fieldset/span[@itemprop="description"]')(self.doc)
if id:
subtitle.id = id
else:
regexp = re.compile(
'https://www.opensubtitles.org/en/subtitles/(?P<id>\d+)/.*$')
result = regexp.match(self.url)
subtitle.id = result.groupdict()['id']
subtitle.name = CleanText('.//div//div//h2')(self.doc)
subtitle.url = self.url
return subtitle
def get_subtitle(self, id=None):
subtitle = Subtitle()
subtitle.description = CleanText('.//fieldset/span[@itemprop="description"]')(self.doc)
if id:
subtitle.id = id
else:
regexp = re.compile('https://www.opensubtitles.org/en/subtitles/(?P<id>\d+)/.*$')
result = regexp.match(self.url)
subtitle.id = result.groupdict()['id']
subtitle.name = CleanText('.//div//div//h2')(self.doc)
subtitle.url = self.url
return subtitle
def get_subtitle(self, id):
language = NotAvailable
url = NotAvailable
nb_cd = NotAvailable
links_info = self.parser.select(self.document.getroot(),
'fieldset.information a')
for link in links_info:
href = link.attrib.get('href', '')
if '/fr/ppodnapisi/kategorija/jezik/' in href:
nlang = href.split('/')[-1]
for lang, langnum in LANGUAGE_NUMBERS.items():
if str(langnum) == str(nlang):
language = unicode(lang)
break
desc = u''
infos = self.parser.select(self.document.getroot(),
'fieldset.information')
for info in infos:
for p in self.parser.select(info, 'p'):
desc += '%s\n' % (u' '.join(p.text_content().strip().split()))
spans = self.parser.select(info, 'span')
for span in spans:
if span.text is not None and 'CD' in span.text:
nb_cd = int(
self.parser.select(span.getparent(), 'span')[1].text)
title = unicode(
self.parser.select(self.document.getroot(), 'head title', 1).text)
name = title.split(' - ')[0]
dllinks = self.parser.select(self.document.getroot(),
'div.footer > a.download')
for link in dllinks:
href = link.attrib.get('href', '')
if id in href:
url = u'http://www.podnapisi.net%s' % href
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.language = language
subtitle.nb_cd = nb_cd
subtitle.description = desc
return subtitle
def get_subtitle(self):
desc = NotAvailable
a = self.parser.select(self.document.getroot(), 'a#bt-dwl-bt', 1)
id = a.attrib.get('data-product-id', '')
m = re.match('Download \((\w+)\)', self.parser.tocleanstring(a))
if m:
ext = m.group(1)
else:
ext = u'zip'
url = unicode('http://www.opensubtitles.org/en/subtitleserve/sub/%s' %
id)
link = self.parser.select(self.document.getroot(),
'link[rel=bookmark]', 1)
title = unicode(link.attrib.get('title', ''))
nb_cd = int(title.lower().split('cd')[0].split()[-1])
lang = unicode(title.split('(')[1].split(')')[0])
file_names = self.parser.select(self.document.getroot(),
"img[title~=filename]")
if len(file_names) > 0:
file_name = file_names[0].getparent().text_content()
file_name = ' '.join(file_name.split())
desc = u'files :'
for f in file_names:
desc_line = f.getparent().text_content()
desc += '\n' + ' '.join(desc_line.split())
name = unicode('%s (%s)' % (title, file_name))
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.ext = ext
for lshort, llong in LANGUAGE_CONV.items():
if lang == llong:
lang = unicode(lshort)
break
subtitle.language = lang
subtitle.nb_cd = nb_cd
subtitle.description = desc
return subtitle
def iter_subtitles(self, language, pattern):
pattern = pattern.strip().replace('+', ' ').lower()
pattern_words = pattern.split()
tab = self.parser.select(self.document.getroot(), 'table[bordercolor="#B8C0B2"]')
if len(tab) == 0:
tab = self.parser.select(self.document.getroot(), 'table[bordercolordark="#B8C0B2"]')
if len(tab) == 0:
return
# some results of freefind point on useless pages
if tab[0].attrib.get('width', '') != '100%':
return
for line in tab[0].getiterator('tr'):
cols = self.parser.select(line, 'td')
traduced_title = self.parser.select(cols[0], 'font', 1).text.lower()
original_title = self.parser.select(cols[1], 'font', 1).text.lower()
traduced_title_words = traduced_title.split()
original_title_words = original_title.split()
# if the pattern is one word and in the title OR if the
# intersection between pattern and the title is at least 2 words
if (len(pattern_words) == 1 and pattern in traduced_title_words) or\
(len(pattern_words) == 1 and pattern in original_title_words) or\
(len(list(set(pattern_words) & set(traduced_title_words))) > 1) or\
(len(list(set(pattern_words) & set(original_title_words))) > 1):
# this is to trash special spacing chars
traduced_title = " ".join(traduced_title_words)
original_title = " ".join(original_title_words)
nb_cd = self.parser.select(cols[2], 'font', 1).text.strip()
nb_cd = int(nb_cd.strip(' CD'))
name = unicode('%s (%s)' % (original_title, traduced_title))
href = self.parser.select(cols[3], 'a', 1).attrib.get('href', '')
url = unicode('http://davidbillemont3.free.fr/%s' % href)
id = unicode('%s|%s' % (self.browser.geturl().split('/')[-1], href))
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.ext = url.split('.')[-1]
subtitle.language = unicode('fr')
subtitle.nb_cd = nb_cd
subtitle.description = NotAvailable
yield subtitle
def get_subtitle_from_line(self, line):
cells = self.parser.select(line, 'td')
if len(cells) > 0:
links = self.parser.select(line, 'a')
a = links[0]
name = u" ".join(a.text.strip().split())
first_cell = cells[0]
spanlist = self.parser.select(first_cell, 'span')
if len(spanlist) > 0:
long_name = spanlist[0].attrib.get('title', '')
else:
texts = first_cell.itertext()
long_name = texts.next()
long_name = texts.next()
if "Download at 25" in long_name:
long_name = "---"
name = "%s (%s)" % (name, long_name)
second_cell = cells[1]
link = self.parser.select(second_cell, 'a', 1)
lang = link.attrib.get('href', '').split('/')[-1].split('-')[-1]
for lshort, llong in LANGUAGE_CONV.items():
if lang == llong:
lang = unicode(lshort)
break
nb_cd = int(cells[2].text.strip().lower().replace('cd', ''))
cell_dl = cells[4]
href = self.parser.select(cell_dl, 'a', 1).attrib.get('href', '')
url = unicode('http://www.opensubtitles.org%s' % href)
id = href.split('/')[-1]
subtitle = Subtitle(id, name)
subtitle.url = url
subtitle.language = lang
subtitle.nb_cd = nb_cd
subtitle.description = NotLoaded
return subtitle