autopep8 with 120 chars line length on my modules
This commit is contained in:
Julien Veyssier
parent
6a7bc0924d
commit
5d923bc73b
39 changed files with 434 additions and 426 deletions
|
|
@ -17,7 +17,7 @@
|
|||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
from weboob.capabilities.recipe import ICapRecipe,Recipe
|
||||
from weboob.capabilities.recipe import ICapRecipe, Recipe
|
||||
from weboob.tools.backend import BaseBackend
|
||||
|
||||
from .browser import SevenFiftyGramsBrowser
|
||||
|
|
@ -46,16 +46,16 @@ class SevenFiftyGramsBackend(BaseBackend, ICapRecipe):
|
|||
def fill_recipe(self, recipe, fields):
|
||||
if 'nb_person' in fields or 'instructions' in fields:
|
||||
rec = self.get_recipe(recipe.id)
|
||||
recipe.picture_url = rec.picture_url
|
||||
recipe.instructions = rec.instructions
|
||||
recipe.ingredients = rec.ingredients
|
||||
recipe.comments = rec.comments
|
||||
recipe.nb_person = rec.nb_person
|
||||
recipe.cooking_time = rec.cooking_time
|
||||
recipe.picture_url = rec.picture_url
|
||||
recipe.instructions = rec.instructions
|
||||
recipe.ingredients = rec.ingredients
|
||||
recipe.comments = rec.comments
|
||||
recipe.nb_person = rec.nb_person
|
||||
recipe.cooking_time = rec.cooking_time
|
||||
recipe.preparation_time = rec.preparation_time
|
||||
|
||||
return recipe
|
||||
|
||||
OBJECTS = {
|
||||
Recipe:fill_recipe,
|
||||
}
|
||||
Recipe: fill_recipe,
|
||||
}
|
||||
|
|
|
|||
|
|
@ -34,10 +34,10 @@ class SevenFiftyGramsBrowser(BaseBrowser):
|
|||
PAGES = {
|
||||
'http://www.750g.com/recettes_.*.htm': ResultsPage,
|
||||
'http://www.750g.com/fiche_de_cuisine_complete.htm\?recettes_id=[0-9]*': RecipePage,
|
||||
}
|
||||
}
|
||||
|
||||
def iter_recipes(self, pattern):
|
||||
self.location('http://www.750g.com/recettes_%s.htm' % (pattern.replace(' ','_')))
|
||||
self.location('http://www.750g.com/recettes_%s.htm' % (pattern.replace(' ', '_')))
|
||||
assert self.is_on_page(ResultsPage)
|
||||
return self.page.iter_recipes()
|
||||
|
||||
|
|
|
|||
|
|
@ -30,35 +30,36 @@ class ResultsPage(BasePage):
|
|||
""" Page which contains results as a list of recipies
|
||||
"""
|
||||
def iter_recipes(self):
|
||||
for div in self.parser.select(self.document.getroot(),'div.recette_description > div.data'):
|
||||
links = self.parser.select(div,'div.info > p.title > a.fn')
|
||||
for div in self.parser.select(self.document.getroot(), 'div.recette_description > div.data'):
|
||||
links = self.parser.select(div, 'div.info > p.title > a.fn')
|
||||
if len(links) > 0:
|
||||
link = links[0]
|
||||
title = unicode(link.text)
|
||||
#id = unicode(link.attrib.get('href','').strip('/').replace('.htm','htm'))
|
||||
id = unicode(self.parser.select(div,'div.carnet-add a',1).attrib.get('href','').split('=')[-1])
|
||||
# id = unicode(link.attrib.get('href','').strip('/').replace('.htm','htm'))
|
||||
id = unicode(self.parser.select(div, 'div.carnet-add a', 1).attrib.get('href', '').split('=')[-1])
|
||||
thumbnail_url = NotAvailable
|
||||
short_description = NotAvailable
|
||||
|
||||
imgs = self.parser.select(div,'img.recipe-image')
|
||||
imgs = self.parser.select(div, 'img.recipe-image')
|
||||
if len(imgs) > 0:
|
||||
thumbnail_url = unicode(imgs[0].attrib.get('src',''))
|
||||
short_description = unicode(' '.join(self.parser.select(div,'div.infos_column',1).text_content().split()).strip())
|
||||
imgs_cost = self.parser.select(div,'div.infos_column img')
|
||||
thumbnail_url = unicode(imgs[0].attrib.get('src', ''))
|
||||
short_description = unicode(' '.join(self.parser.select(
|
||||
div, 'div.infos_column', 1).text_content().split()).strip())
|
||||
imgs_cost = self.parser.select(div, 'div.infos_column img')
|
||||
cost_tot = len(imgs_cost)
|
||||
cost_on = 0
|
||||
for img in imgs_cost:
|
||||
if img.attrib.get('src','').endswith('euro_on.png'):
|
||||
if img.attrib.get('src', '').endswith('euro_on.png'):
|
||||
cost_on += 1
|
||||
short_description += u' %s/%s'%(cost_on,cost_tot)
|
||||
short_description += u' %s/%s' % (cost_on, cost_tot)
|
||||
|
||||
recipe = Recipe(id,title)
|
||||
recipe = Recipe(id, title)
|
||||
recipe.thumbnail_url = thumbnail_url
|
||||
recipe.short_description= short_description
|
||||
recipe.instructions = NotLoaded
|
||||
recipe.ingredients = NotLoaded
|
||||
recipe.nb_person = NotLoaded
|
||||
recipe.cooking_time = NotLoaded
|
||||
recipe.short_description = short_description
|
||||
recipe.instructions = NotLoaded
|
||||
recipe.ingredients = NotLoaded
|
||||
recipe.nb_person = NotLoaded
|
||||
recipe.cooking_time = NotLoaded
|
||||
recipe.preparation_time = NotLoaded
|
||||
yield recipe
|
||||
|
||||
|
|
@ -76,10 +77,10 @@ class RecipePage(BasePage):
|
|||
instructions = NotAvailable
|
||||
comments = []
|
||||
|
||||
title = unicode(self.parser.select(self.document.getroot(),'head > title',1).text.split(' - ')[1])
|
||||
main = self.parser.select(self.document.getroot(),'div.recette_description',1)
|
||||
title = unicode(self.parser.select(self.document.getroot(), 'head > title', 1).text.split(' - ')[1])
|
||||
main = self.parser.select(self.document.getroot(), 'div.recette_description', 1)
|
||||
|
||||
rec_infos = self.parser.select(self.document.getroot(),'div.recette_infos div.infos_column strong')
|
||||
rec_infos = self.parser.select(self.document.getroot(), 'div.recette_infos div.infos_column strong')
|
||||
for info_title in rec_infos:
|
||||
if u'Temps de préparation' in unicode(info_title.text):
|
||||
if info_title.tail.strip() != '':
|
||||
|
|
@ -96,31 +97,31 @@ class RecipePage(BasePage):
|
|||
nb_person = int(info_title.tail)
|
||||
|
||||
ingredients = []
|
||||
p_ing = self.parser.select(main,'div.data.top.left > div.content p')
|
||||
p_ing = self.parser.select(main, 'div.data.top.left > div.content p')
|
||||
for ing in p_ing:
|
||||
ingtxt = unicode(ing.text_content().strip())
|
||||
if ingtxt != '':
|
||||
ingredients.append(ingtxt)
|
||||
|
||||
lines_instr = self.parser.select(main,'div.data.top.right div.content li')
|
||||
lines_instr = self.parser.select(main, 'div.data.top.right div.content li')
|
||||
if len(lines_instr) > 0:
|
||||
instructions = u''
|
||||
for line in lines_instr:
|
||||
inst = ' '.join(line.text_content().strip().split())
|
||||
instructions += '%s\n'% inst
|
||||
instructions += '%s\n' % inst
|
||||
instructions = instructions.strip('\n')
|
||||
|
||||
imgillu = self.parser.select(self.document.getroot(),'div.resume_recette_illustree img.photo')
|
||||
imgillu = self.parser.select(self.document.getroot(), 'div.resume_recette_illustree img.photo')
|
||||
if len(imgillu) > 0:
|
||||
picture_url = unicode(imgillu[0].attrib.get('src',''))
|
||||
picture_url = unicode(imgillu[0].attrib.get('src', ''))
|
||||
|
||||
for divcom in self.parser.select(self.document.getroot(),'div.comment-outer'):
|
||||
for divcom in self.parser.select(self.document.getroot(), 'div.comment-outer'):
|
||||
comtxt = unicode(' '.join(divcom.text_content().strip().split()))
|
||||
if u'| Répondre' in comtxt:
|
||||
comtxt = comtxt.strip('0123456789').replace(u' | Répondre','')
|
||||
comtxt = comtxt.strip('0123456789').replace(u' | Répondre', '')
|
||||
comments.append(comtxt)
|
||||
|
||||
recipe = Recipe(id,title)
|
||||
recipe = Recipe(id, title)
|
||||
recipe.preparation_time = preparation_time
|
||||
recipe.cooking_time = cooking_time
|
||||
recipe.nb_person = nb_person
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@
|
|||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
from weboob.capabilities.subtitle import ICapSubtitle,LanguageNotSupported
|
||||
from weboob.capabilities.subtitle import ICapSubtitle, LanguageNotSupported
|
||||
from weboob.tools.backend import BaseBackend
|
||||
|
||||
from .browser import AttilasubBrowser
|
||||
|
|
@ -53,4 +53,4 @@ class AttilasubBackend(BaseBackend, ICapSubtitle):
|
|||
def iter_subtitles(self, language, pattern):
|
||||
if language not in self.LANGUAGE_LIST:
|
||||
raise LanguageNotSupported()
|
||||
return self.browser.iter_subtitles(language,quote_plus(pattern.encode('utf-8')))
|
||||
return self.browser.iter_subtitles(language, quote_plus(pattern.encode('utf-8')))
|
||||
|
|
|
|||
|
|
@ -34,12 +34,13 @@ class AttilasubBrowser(BaseBrowser):
|
|||
PAGES = {
|
||||
'http://search.freefind.com/find.html.*': SearchPage,
|
||||
'http://davidbillemont3.free.fr/.*.htm': SubtitlesPage,
|
||||
}
|
||||
}
|
||||
|
||||
def iter_subtitles(self, language, pattern):
|
||||
self.location('http://search.freefind.com/find.html?id=81131980&_charset_=&bcd=%%F7&scs=1&pageid=r&query=%s&mode=Find%%20pages%%20matching%%20ALL%%20words' % pattern.encode('utf-8'))
|
||||
self.location('http://search.freefind.com/find.html?id=81131980&_charset_=&bcd=%%F7&scs=1&pageid=r&query=%s&mode=Find%%20pages%%20matching%%20ALL%%20words' %
|
||||
pattern.encode('utf-8'))
|
||||
assert self.is_on_page(SearchPage)
|
||||
return self.page.iter_subtitles(language,pattern)
|
||||
return self.page.iter_subtitles(language, pattern)
|
||||
|
||||
def get_subtitle(self, id):
|
||||
url_end = id.split('|')[0]
|
||||
|
|
|
|||
|
|
@ -23,16 +23,16 @@ from weboob.capabilities.base import NotAvailable
|
|||
from weboob.tools.browser import BasePage
|
||||
|
||||
|
||||
__all__ = ['SubtitlesPage','SearchPage']
|
||||
__all__ = ['SubtitlesPage', 'SearchPage']
|
||||
|
||||
|
||||
class SearchPage(BasePage):
|
||||
def iter_subtitles(self, language, pattern):
|
||||
fontresult = self.parser.select(self.document.getroot(),'div.search-results font.search-results')
|
||||
fontresult = self.parser.select(self.document.getroot(), 'div.search-results font.search-results')
|
||||
# for each result in freefind, explore the subtitle list page to iter subtitles
|
||||
for res in fontresult:
|
||||
a = self.parser.select(res,'a',1)
|
||||
url = a.attrib.get('href','')
|
||||
a = self.parser.select(res, 'a', 1)
|
||||
url = a.attrib.get('href', '')
|
||||
self.browser.location(url)
|
||||
assert self.browser.is_on_page(SubtitlesPage)
|
||||
# subtitles page does the job
|
||||
|
|
@ -41,15 +41,15 @@ class SearchPage(BasePage):
|
|||
|
||||
|
||||
class SubtitlesPage(BasePage):
|
||||
def get_subtitle(self,id):
|
||||
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)
|
||||
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()
|
||||
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()
|
||||
|
|
@ -59,30 +59,30 @@ class SubtitlesPage(BasePage):
|
|||
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)
|
||||
name = unicode('%s (%s)' % (original_title, traduced_title))
|
||||
url = unicode('http://davidbillemont3.free.fr/%s' % href)
|
||||
subtitle = Subtitle(id, name)
|
||||
subtitle.url = url
|
||||
subtitle.language = unicode('fr')
|
||||
subtitle.nb_cd = nb_cd
|
||||
subtitle.description = NotAvailable
|
||||
return subtitle
|
||||
|
||||
def iter_subtitles(self,language, pattern):
|
||||
pattern = pattern.strip().replace('+',' ').lower()
|
||||
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"]')
|
||||
tab = self.parser.select(self.document.getroot(), 'table[bordercolor="#B8C0B2"]')
|
||||
if len(tab) == 0:
|
||||
tab = self.parser.select(self.document.getroot(),'table[bordercolordark="#B8C0B2"]')
|
||||
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%':
|
||||
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()
|
||||
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()
|
||||
|
|
@ -98,13 +98,13 @@ class SubtitlesPage(BasePage):
|
|||
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 = 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)
|
||||
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.language = unicode('fr')
|
||||
subtitle.nb_cd = nb_cd
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ class AttilasubTest(BackendTest):
|
|||
BACKEND = 'attilasub'
|
||||
|
||||
def test_subtitle(self):
|
||||
subtitles = list(self.backend.iter_subtitles('fr','spiderman'))
|
||||
subtitles = list(self.backend.iter_subtitles('fr', 'spiderman'))
|
||||
assert (len(subtitles) > 0)
|
||||
for subtitle in subtitles:
|
||||
path, qs = urllib.splitquery(subtitle.url)
|
||||
|
|
|
|||
|
|
@ -67,25 +67,25 @@ class ImdbBackend(BaseBackend, ICapCinema):
|
|||
return self.browser.get_person_biography(id)
|
||||
|
||||
def get_movie_releases(self, id, country=None):
|
||||
return self.browser.get_movie_releases(id,country)
|
||||
return self.browser.get_movie_releases(id, country)
|
||||
|
||||
def fill_person(self, person, fields):
|
||||
if 'real_name' in fields or 'birth_place' in fields\
|
||||
or 'death_date' in fields or 'nationality' in fields\
|
||||
or 'short_biography' in fields or 'roles' in fields\
|
||||
or 'birth_date' in fields or 'thumbnail_url' in fields\
|
||||
or 'gender' in fields or fields is None:
|
||||
or 'death_date' in fields or 'nationality' in fields\
|
||||
or 'short_biography' in fields or 'roles' in fields\
|
||||
or 'birth_date' in fields or 'thumbnail_url' in fields\
|
||||
or 'gender' in fields or fields is None:
|
||||
per = self.get_person(person.id)
|
||||
person.real_name = per.real_name
|
||||
person.birth_date = per.birth_date
|
||||
person.death_date = per.death_date
|
||||
person.birth_place = per.birth_place
|
||||
person.gender = per.gender
|
||||
person.nationality = per.nationality
|
||||
person.real_name = per.real_name
|
||||
person.birth_date = per.birth_date
|
||||
person.death_date = per.death_date
|
||||
person.birth_place = per.birth_place
|
||||
person.gender = per.gender
|
||||
person.nationality = per.nationality
|
||||
person.short_biography = per.short_biography
|
||||
person.short_description = per.short_description
|
||||
person.roles = per.roles
|
||||
person.thumbnail_url = per.thumbnail_url
|
||||
person.roles = per.roles
|
||||
person.thumbnail_url = per.thumbnail_url
|
||||
|
||||
if 'biography' in fields:
|
||||
person.biography = self.get_person_biography(person.id)
|
||||
|
|
@ -94,19 +94,19 @@ class ImdbBackend(BaseBackend, ICapCinema):
|
|||
|
||||
def fill_movie(self, movie, fields):
|
||||
if 'other_titles' in fields or 'release_date' in fields\
|
||||
or 'duration' in fields or 'country' in fields\
|
||||
or 'roles' in fields or 'note' in fields\
|
||||
or 'thumbnail_url' in fields:
|
||||
or 'duration' in fields or 'country' in fields\
|
||||
or 'roles' in fields or 'note' in fields\
|
||||
or 'thumbnail_url' in fields:
|
||||
mov = self.get_movie(movie.id)
|
||||
movie.other_titles = mov.other_titles
|
||||
movie.release_date = mov.release_date
|
||||
movie.duration = mov.duration
|
||||
movie.pitch = mov.pitch
|
||||
movie.country = mov.country
|
||||
movie.note = mov.note
|
||||
movie.roles = mov.roles
|
||||
movie.short_description= mov.short_description
|
||||
movie.thumbnail_url = mov.thumbnail_url
|
||||
movie.other_titles = mov.other_titles
|
||||
movie.release_date = mov.release_date
|
||||
movie.duration = mov.duration
|
||||
movie.pitch = mov.pitch
|
||||
movie.country = mov.country
|
||||
movie.note = mov.note
|
||||
movie.roles = mov.roles
|
||||
movie.short_description = mov.short_description
|
||||
movie.thumbnail_url = mov.thumbnail_url
|
||||
|
||||
if 'all_release_dates' in fields:
|
||||
movie.all_release_dates = self.get_movie_releases(movie.id)
|
||||
|
|
@ -114,6 +114,6 @@ class ImdbBackend(BaseBackend, ICapCinema):
|
|||
return movie
|
||||
|
||||
OBJECTS = {
|
||||
Person:fill_person,
|
||||
Movie:fill_movie
|
||||
}
|
||||
Person: fill_person,
|
||||
Movie: fill_movie
|
||||
}
|
||||
|
|
|
|||
|
|
@ -42,53 +42,55 @@ class ImdbBrowser(BaseBrowser):
|
|||
'http://www.imdb.com/name/nm[0-9]*/*': PersonPage,
|
||||
'http://www.imdb.com/name/nm[0-9]*/bio.*': BiographyPage,
|
||||
'http://www.imdb.com/name/nm[0-9]*/filmo.*': FilmographyPage,
|
||||
}
|
||||
}
|
||||
|
||||
def iter_movies(self, pattern):
|
||||
res = self.readurl('http://www.imdb.com/xml/find?json=1&nr=1&tt=on&q=%s' % pattern.encode('utf-8'))
|
||||
jres = json.loads(res)
|
||||
for cat in ['title_popular','title_exact','title_approx']:
|
||||
for cat in ['title_popular', 'title_exact', 'title_approx']:
|
||||
if cat in jres:
|
||||
for m in jres[cat]:
|
||||
tdesc = unicode(m['title_description'])
|
||||
if '<a' in tdesc and '>' in tdesc:
|
||||
short_description = u'%s %s'%(tdesc.split('<')[0].strip(', '), tdesc.split('>')[1].split('<')[0])
|
||||
short_description = u'%s %s' % (tdesc.split('<')[
|
||||
0].strip(', '), tdesc.split('>')[1].split('<')[0])
|
||||
else:
|
||||
short_description = tdesc.strip(', ')
|
||||
movie = Movie(m['id'],latin2unicode(m['title']))
|
||||
movie.other_titles = NotLoaded
|
||||
movie.release_date = NotLoaded
|
||||
movie.duration = NotLoaded
|
||||
movie = Movie(m['id'], latin2unicode(m['title']))
|
||||
movie.other_titles = NotLoaded
|
||||
movie.release_date = NotLoaded
|
||||
movie.duration = NotLoaded
|
||||
movie.short_description = latin2unicode(short_description)
|
||||
movie.pitch = NotLoaded
|
||||
movie.country = NotLoaded
|
||||
movie.note = NotLoaded
|
||||
movie.roles = NotLoaded
|
||||
movie.all_release_dates= NotLoaded
|
||||
movie.thumbnail_url = NotLoaded
|
||||
movie.pitch = NotLoaded
|
||||
movie.country = NotLoaded
|
||||
movie.note = NotLoaded
|
||||
movie.roles = NotLoaded
|
||||
movie.all_release_dates = NotLoaded
|
||||
movie.thumbnail_url = NotLoaded
|
||||
yield movie
|
||||
|
||||
def iter_persons(self, pattern):
|
||||
res = self.readurl('http://www.imdb.com/xml/find?json=1&nr=1&nm=on&q=%s' % pattern.encode('utf-8'))
|
||||
jres = json.loads(res)
|
||||
for cat in ['name_popular','name_exact','name_approx']:
|
||||
for cat in ['name_popular', 'name_exact', 'name_approx']:
|
||||
if cat in jres:
|
||||
for p in jres[cat]:
|
||||
person = Person(p['id'],latin2unicode(p['name']))
|
||||
person.real_name = NotLoaded
|
||||
person.birth_place = NotLoaded
|
||||
person.birth_date = NotLoaded
|
||||
person.death_date = NotLoaded
|
||||
person.gender = NotLoaded
|
||||
person.nationality = NotLoaded
|
||||
person.short_biography= NotLoaded
|
||||
person.short_description= latin2unicode(p['description'])
|
||||
person.roles = NotLoaded
|
||||
person.thumbnail_url = NotLoaded
|
||||
person = Person(p['id'], latin2unicode(p['name']))
|
||||
person.real_name = NotLoaded
|
||||
person.birth_place = NotLoaded
|
||||
person.birth_date = NotLoaded
|
||||
person.death_date = NotLoaded
|
||||
person.gender = NotLoaded
|
||||
person.nationality = NotLoaded
|
||||
person.short_biography = NotLoaded
|
||||
person.short_description = latin2unicode(p['description'])
|
||||
person.roles = NotLoaded
|
||||
person.thumbnail_url = NotLoaded
|
||||
yield person
|
||||
|
||||
def get_movie(self, id):
|
||||
res = self.readurl('http://imdbapi.org/?id=%s&type=json&plot=simple&episode=1&lang=en-US&aka=full&release=simple&business=0&tech=0' % id )
|
||||
res = self.readurl(
|
||||
'http://imdbapi.org/?id=%s&type=json&plot=simple&episode=1&lang=en-US&aka=full&release=simple&business=0&tech=0' % id)
|
||||
if res is not None:
|
||||
jres = json.loads(res)
|
||||
else:
|
||||
|
|
@ -122,7 +124,7 @@ class ImdbBrowser(BaseBrowser):
|
|||
if 'also_known_as' in jres:
|
||||
for other_t in jres['also_known_as']:
|
||||
if 'country' in other_t and 'title' in other_t:
|
||||
other_titles.append('%s : %s' % (other_t['country'],htmlparser.unescape(other_t['title'])))
|
||||
other_titles.append('%s : %s' % (other_t['country'], htmlparser.unescape(other_t['title'])))
|
||||
if 'release_date' in jres:
|
||||
dstr = str(jres['release_date'])
|
||||
year = int(dstr[:4])
|
||||
|
|
@ -134,31 +136,31 @@ class ImdbBrowser(BaseBrowser):
|
|||
day = int(dstr[-2:])
|
||||
if day == 0:
|
||||
day = 1
|
||||
release_date = datetime(year,month,day)
|
||||
release_date = datetime(year, month, day)
|
||||
if 'country' in jres:
|
||||
country = u''
|
||||
for c in jres['country']:
|
||||
country += '%s, '%c
|
||||
country += '%s, ' % c
|
||||
country = country[:-2]
|
||||
if 'plot_simple' in jres:
|
||||
pitch = unicode(jres['plot_simple'])
|
||||
if 'rating' in jres and 'rating_count' in jres:
|
||||
note = u'%s/10 (%s votes)'%(jres['rating'],jres['rating_count'])
|
||||
for r in ['actor','director','writer']:
|
||||
if '%ss'%r in jres:
|
||||
roles['%s'%r] = list(jres['%ss'%r])
|
||||
note = u'%s/10 (%s votes)' % (jres['rating'], jres['rating_count'])
|
||||
for r in ['actor', 'director', 'writer']:
|
||||
if '%ss' % r in jres:
|
||||
roles['%s' % r] = list(jres['%ss' % r])
|
||||
|
||||
movie = Movie(id,title)
|
||||
movie.other_titles = other_titles
|
||||
movie.release_date = release_date
|
||||
movie.duration = duration
|
||||
movie.pitch = pitch
|
||||
movie.country = country
|
||||
movie.note = note
|
||||
movie.roles = roles
|
||||
movie.short_description= short_description
|
||||
movie.all_release_dates= NotLoaded
|
||||
movie.thumbnail_url = thumbnail_url
|
||||
movie = Movie(id, title)
|
||||
movie.other_titles = other_titles
|
||||
movie.release_date = release_date
|
||||
movie.duration = duration
|
||||
movie.pitch = pitch
|
||||
movie.country = country
|
||||
movie.note = note
|
||||
movie.roles = roles
|
||||
movie.short_description = short_description
|
||||
movie.all_release_dates = NotLoaded
|
||||
movie.thumbnail_url = thumbnail_url
|
||||
return movie
|
||||
|
||||
def get_person(self, id):
|
||||
|
|
@ -175,7 +177,7 @@ class ImdbBrowser(BaseBrowser):
|
|||
return self.page.get_biography()
|
||||
|
||||
def iter_movie_persons(self, movie_id, role):
|
||||
self.location('http://www.imdb.com/title/%s/fullcredits'%movie_id)
|
||||
self.location('http://www.imdb.com/title/%s/fullcredits' % movie_id)
|
||||
assert self.is_on_page(MovieCrewPage)
|
||||
for p in self.page.iter_persons(role):
|
||||
yield p
|
||||
|
|
@ -192,13 +194,13 @@ class ImdbBrowser(BaseBrowser):
|
|||
yield movie
|
||||
|
||||
def iter_movie_persons_ids(self, movie_id):
|
||||
self.location('http://www.imdb.com/title/%s/fullcredits'%movie_id)
|
||||
self.location('http://www.imdb.com/title/%s/fullcredits' % movie_id)
|
||||
assert self.is_on_page(MovieCrewPage)
|
||||
for person in self.page.iter_persons_ids():
|
||||
yield person
|
||||
|
||||
def get_movie_releases(self,id, country):
|
||||
self.location('http://www.imdb.com/title/%s/releaseinfo'%id)
|
||||
def get_movie_releases(self, id, country):
|
||||
self.location('http://www.imdb.com/title/%s/releaseinfo' % id)
|
||||
assert self.is_on_page(ReleasePage)
|
||||
return self.page.get_movie_releases(country)
|
||||
|
||||
|
|
@ -222,5 +224,5 @@ dict_hex = {'á': u'á',
|
|||
|
||||
def latin2unicode(word):
|
||||
for key in dict_hex.keys():
|
||||
word = word.replace(key,dict_hex[key])
|
||||
word = word.replace(key, dict_hex[key])
|
||||
return unicode(word)
|
||||
|
|
|
|||
|
|
@ -25,28 +25,28 @@ from weboob.tools.browser import BasePage
|
|||
from datetime import datetime
|
||||
|
||||
|
||||
__all__ = ['PersonPage','MovieCrewPage','BiographyPage','FilmographyPage','ReleasePage']
|
||||
__all__ = ['PersonPage', 'MovieCrewPage', 'BiographyPage', 'FilmographyPage', 'ReleasePage']
|
||||
|
||||
|
||||
class ReleasePage(BasePage):
|
||||
''' Page containing releases of a movie
|
||||
'''
|
||||
def get_movie_releases(self,country_filter):
|
||||
def get_movie_releases(self, country_filter):
|
||||
result = unicode()
|
||||
links = self.parser.select(self.document.getroot(),'b a')
|
||||
links = self.parser.select(self.document.getroot(), 'b a')
|
||||
for a in links:
|
||||
href = a.attrib.get('href','')
|
||||
href = a.attrib.get('href', '')
|
||||
if href.strip('/').split('/')[0] == 'calendar' and\
|
||||
(country_filter is None or href.split('region=')[-1].lower() == country_filter):
|
||||
(country_filter is None or href.split('region=')[-1].lower() == country_filter):
|
||||
country = a.text
|
||||
td_date = self.parser.select(a.getparent().getparent().getparent(),'td')[1]
|
||||
date_links = self.parser.select(td_date,'a')
|
||||
td_date = self.parser.select(a.getparent().getparent().getparent(), 'td')[1]
|
||||
date_links = self.parser.select(td_date, 'a')
|
||||
if len(date_links) > 1:
|
||||
date = date_links[1].attrib.get('href','').strip('/').split('/')[-1]
|
||||
date += '-'+date_links[0].attrib.get('href','').strip('/').split('/')[-1]
|
||||
date = date_links[1].attrib.get('href', '').strip('/').split('/')[-1]
|
||||
date += '-'+date_links[0].attrib.get('href', '').strip('/').split('/')[-1]
|
||||
else:
|
||||
date = unicode(self.parser.select(a.getparent().getparent().getparent(),'td')[1].text_content())
|
||||
result += '%s : %s\n' % (country,date)
|
||||
date = unicode(self.parser.select(a.getparent().getparent().getparent(), 'td')[1].text_content())
|
||||
result += '%s : %s\n' % (country, date)
|
||||
if result == u'':
|
||||
result = NotAvailable
|
||||
else:
|
||||
|
|
@ -59,11 +59,11 @@ class BiographyPage(BasePage):
|
|||
'''
|
||||
def get_biography(self):
|
||||
bio = unicode()
|
||||
tn = self.parser.select(self.document.getroot(),'div#tn15content',1)
|
||||
tn = self.parser.select(self.document.getroot(), 'div#tn15content', 1)
|
||||
# we only read paragraphs, titles and links
|
||||
for ch in tn.getchildren():
|
||||
if ch.tag in ['p','h5','a']:
|
||||
bio += '%s\n\n'%ch.text_content().strip()
|
||||
if ch.tag in ['p', 'h5', 'a']:
|
||||
bio += '%s\n\n' % ch.text_content().strip()
|
||||
if bio == u'':
|
||||
bio = NotAvailable
|
||||
return bio
|
||||
|
|
@ -74,52 +74,52 @@ class MovieCrewPage(BasePage):
|
|||
'''
|
||||
def iter_persons(self, role_filter=None):
|
||||
if (role_filter is None or (role_filter is not None and role_filter == 'actor')):
|
||||
tables = self.parser.select(self.document.getroot(),'table.cast')
|
||||
tables = self.parser.select(self.document.getroot(), 'table.cast')
|
||||
if len(tables) > 0:
|
||||
table = tables[0]
|
||||
tds = self.parser.select(table,'td.nm')
|
||||
tds = self.parser.select(table, 'td.nm')
|
||||
for td in tds:
|
||||
id = td.find('a').attrib.get('href','').strip('/').split('/')[-1]
|
||||
id = td.find('a').attrib.get('href', '').strip('/').split('/')[-1]
|
||||
name = unicode(td.find('a').text)
|
||||
char_name = unicode(self.parser.select(td.getparent(),'td.char',1).text_content())
|
||||
person = Person(id,name)
|
||||
char_name = unicode(self.parser.select(td.getparent(), 'td.char', 1).text_content())
|
||||
person = Person(id, name)
|
||||
person.short_description = char_name
|
||||
person.real_name = NotLoaded
|
||||
person.birth_place = NotLoaded
|
||||
person.birth_date = NotLoaded
|
||||
person.death_date = NotLoaded
|
||||
person.gender = NotLoaded
|
||||
person.nationality = NotLoaded
|
||||
person.short_biography= NotLoaded
|
||||
person.roles = NotLoaded
|
||||
person.thumbnail_url = NotLoaded
|
||||
person.real_name = NotLoaded
|
||||
person.birth_place = NotLoaded
|
||||
person.birth_date = NotLoaded
|
||||
person.death_date = NotLoaded
|
||||
person.gender = NotLoaded
|
||||
person.nationality = NotLoaded
|
||||
person.short_biography = NotLoaded
|
||||
person.roles = NotLoaded
|
||||
person.thumbnail_url = NotLoaded
|
||||
yield person
|
||||
|
||||
for gloss_link in self.parser.select(self.document.getroot(),'table[cellspacing=1] h5 a'):
|
||||
role = gloss_link.attrib.get('name','').rstrip('s')
|
||||
for gloss_link in self.parser.select(self.document.getroot(), 'table[cellspacing=1] h5 a'):
|
||||
role = gloss_link.attrib.get('name', '').rstrip('s')
|
||||
if (role_filter is None or (role_filter is not None and role == role_filter)):
|
||||
tbody = gloss_link.getparent().getparent().getparent().getparent()
|
||||
for line in self.parser.select(tbody,'tr')[1:]:
|
||||
for a in self.parser.select(line,'a'):
|
||||
for line in self.parser.select(tbody, 'tr')[1:]:
|
||||
for a in self.parser.select(line, 'a'):
|
||||
role_detail = NotAvailable
|
||||
href = a.attrib.get('href','')
|
||||
href = a.attrib.get('href', '')
|
||||
if '/name/nm' in href:
|
||||
id = href.strip('/').split('/')[-1]
|
||||
name = unicode(a.text)
|
||||
if 'glossary' in href:
|
||||
role_detail = unicode(a.text)
|
||||
person = Person(id,name)
|
||||
person = Person(id, name)
|
||||
person.short_description = role_detail
|
||||
yield person
|
||||
#yield self.browser.get_person(id)
|
||||
# yield self.browser.get_person(id)
|
||||
|
||||
def iter_persons_ids(self):
|
||||
tables = self.parser.select(self.document.getroot(),'table.cast')
|
||||
tables = self.parser.select(self.document.getroot(), 'table.cast')
|
||||
if len(tables) > 0:
|
||||
table = tables[0]
|
||||
tds = self.parser.select(table,'td.nm')
|
||||
tds = self.parser.select(table, 'td.nm')
|
||||
for td in tds:
|
||||
id = td.find('a').attrib.get('href','').strip('/').split('/')[-1]
|
||||
id = td.find('a').attrib.get('href', '').strip('/').split('/')[-1]
|
||||
yield id
|
||||
|
||||
|
||||
|
|
@ -127,7 +127,7 @@ class PersonPage(BasePage):
|
|||
''' Page giving informations about a person
|
||||
It is used to build a Person instance and to get the movie list related to a person
|
||||
'''
|
||||
def get_person(self,id):
|
||||
def get_person(self, id):
|
||||
name = NotAvailable
|
||||
short_biography = NotAvailable
|
||||
short_description = NotAvailable
|
||||
|
|
@ -139,52 +139,52 @@ class PersonPage(BasePage):
|
|||
thumbnail_url = NotAvailable
|
||||
roles = {}
|
||||
nationality = NotAvailable
|
||||
td_overview = self.parser.select(self.document.getroot(),'td#overview-top',1)
|
||||
descs = self.parser.select(td_overview,'span[itemprop=description]')
|
||||
td_overview = self.parser.select(self.document.getroot(), 'td#overview-top', 1)
|
||||
descs = self.parser.select(td_overview, 'span[itemprop=description]')
|
||||
if len(descs) > 0:
|
||||
short_biography = unicode(descs[0].text)
|
||||
rname_block = self.parser.select(td_overview,'div.txt-block h4.inline')
|
||||
rname_block = self.parser.select(td_overview, 'div.txt-block h4.inline')
|
||||
if len(rname_block) > 0 and "born" in rname_block[0].text.lower():
|
||||
links = self.parser.select(rname_block[0].getparent(),'a')
|
||||
links = self.parser.select(rname_block[0].getparent(), 'a')
|
||||
for a in links:
|
||||
href = a.attrib.get('href','').strip()
|
||||
href = a.attrib.get('href', '').strip()
|
||||
if href == 'bio':
|
||||
real_name = unicode(a.text.strip())
|
||||
elif 'birth_place' in href:
|
||||
birth_place = unicode(a.text.lower().strip())
|
||||
names = self.parser.select(td_overview,'h1[itemprop=name]')
|
||||
names = self.parser.select(td_overview, 'h1[itemprop=name]')
|
||||
if len(names) > 0:
|
||||
name = unicode(names[0].text.strip())
|
||||
times = self.parser.select(td_overview,'time[itemprop=birthDate]')
|
||||
times = self.parser.select(td_overview, 'time[itemprop=birthDate]')
|
||||
if len(times) > 0:
|
||||
time = times[0].attrib.get('datetime','').split('-')
|
||||
time = times[0].attrib.get('datetime', '').split('-')
|
||||
if len(time) == 3 and int(time[0]) >= 1900:
|
||||
birth_date = datetime(int(time[0]),int(time[1]),int(time[2]))
|
||||
dtimes = self.parser.select(td_overview,'time[itemprop=deathDate]')
|
||||
birth_date = datetime(int(time[0]), int(time[1]), int(time[2]))
|
||||
dtimes = self.parser.select(td_overview, 'time[itemprop=deathDate]')
|
||||
if len(dtimes) > 0:
|
||||
dtime = dtimes[0].attrib.get('datetime','').split('-')
|
||||
dtime = dtimes[0].attrib.get('datetime', '').split('-')
|
||||
if len(dtime) == 3 and int(dtime[0]) >= 1900:
|
||||
death_date = datetime(int(dtime[0]),int(dtime[1]),int(dtime[2]))
|
||||
img_thumbnail = self.parser.select(self.document.getroot(),'td#img_primary img')
|
||||
death_date = datetime(int(dtime[0]), int(dtime[1]), int(dtime[2]))
|
||||
img_thumbnail = self.parser.select(self.document.getroot(), 'td#img_primary img')
|
||||
if len(img_thumbnail) > 0:
|
||||
thumbnail_url = unicode(img_thumbnail[0].attrib.get('src',''))
|
||||
thumbnail_url = unicode(img_thumbnail[0].attrib.get('src', ''))
|
||||
|
||||
# go to the filmography page
|
||||
self.browser.location('http://www.imdb.com/name/%s/filmotype'%id)
|
||||
self.browser.location('http://www.imdb.com/name/%s/filmotype' % id)
|
||||
assert self.browser.is_on_page(FilmographyPage)
|
||||
roles = self.browser.page.get_roles()
|
||||
|
||||
person = Person(id,name)
|
||||
person.real_name = real_name
|
||||
person.birth_date = birth_date
|
||||
person.death_date = death_date
|
||||
person.birth_place = birth_place
|
||||
person.gender = gender
|
||||
person.nationality = nationality
|
||||
person = Person(id, name)
|
||||
person.real_name = real_name
|
||||
person.birth_date = birth_date
|
||||
person.death_date = death_date
|
||||
person.birth_place = birth_place
|
||||
person.gender = gender
|
||||
person.nationality = nationality
|
||||
person.short_biography = short_biography
|
||||
person.short_description = short_description
|
||||
person.roles = roles
|
||||
person.thumbnail_url = thumbnail_url
|
||||
person.roles = roles
|
||||
person.thumbnail_url = thumbnail_url
|
||||
return person
|
||||
|
||||
|
||||
|
|
@ -193,39 +193,39 @@ class FilmographyPage(BasePage):
|
|||
This page is easier to parse than the main person page filmography
|
||||
'''
|
||||
def iter_movies_ids(self):
|
||||
for role_div in self.parser.select(self.document.getroot(),'div.filmo'):
|
||||
for a in self.parser.select(role_div,'ol > li > a'):
|
||||
id = a.attrib.get('href','').strip('/').split('/')[-1]
|
||||
for role_div in self.parser.select(self.document.getroot(), 'div.filmo'):
|
||||
for a in self.parser.select(role_div, 'ol > li > a'):
|
||||
id = a.attrib.get('href', '').strip('/').split('/')[-1]
|
||||
if id.startswith('tt'):
|
||||
yield id
|
||||
|
||||
def get_roles(self):
|
||||
roles = {}
|
||||
for role_div in self.parser.select(self.document.getroot(),'div.filmo'):
|
||||
role = self.parser.select(role_div,'h5 a',1).text.replace(':','')
|
||||
for role_div in self.parser.select(self.document.getroot(), 'div.filmo'):
|
||||
role = self.parser.select(role_div, 'h5 a', 1).text.replace(':', '')
|
||||
roles[role] = []
|
||||
for a in self.parser.select(role_div,'ol > li > a'):
|
||||
id = a.attrib.get('href','').strip('/').split('/')[-1]
|
||||
for a in self.parser.select(role_div, 'ol > li > a'):
|
||||
id = a.attrib.get('href', '').strip('/').split('/')[-1]
|
||||
if id.startswith('tt'):
|
||||
if '(' in a.tail and ')' in a.tail:
|
||||
between_p = a.tail.split(')')[0].split('(')[1]
|
||||
else:
|
||||
between_p = '????'
|
||||
roles[role].append('(%s) %s'%(between_p,a.text))
|
||||
roles[role].append('(%s) %s' % (between_p, a.text))
|
||||
return roles
|
||||
|
||||
def iter_movies(self, role_filter=None):
|
||||
for role_div in self.parser.select(self.document.getroot(),'div.filmo'):
|
||||
role = self.parser.select(role_div,'h5 a',1).text.replace(':','')
|
||||
for role_div in self.parser.select(self.document.getroot(), 'div.filmo'):
|
||||
role = self.parser.select(role_div, 'h5 a', 1).text.replace(':', '')
|
||||
if (role_filter is None or (role_filter is not None and role.lower().strip() == role_filter))\
|
||||
and role != 'In Development':
|
||||
for a in self.parser.select(role_div,'ol > li > a'):
|
||||
id = a.attrib.get('href','').strip('/').split('/')[-1]
|
||||
and role != 'In Development':
|
||||
for a in self.parser.select(role_div, 'ol > li > a'):
|
||||
id = a.attrib.get('href', '').strip('/').split('/')[-1]
|
||||
if id.startswith('tt'):
|
||||
title = unicode(a.text)
|
||||
role_detail = NotAvailable
|
||||
if len(a.tail) > 0:
|
||||
role_detail = unicode(' '.join(a.tail.replace('..','').split()))
|
||||
movie = Movie(id,title)
|
||||
role_detail = unicode(' '.join(a.tail.replace('..', '').split()))
|
||||
movie = Movie(id, title)
|
||||
movie.short_description = role_detail
|
||||
yield movie
|
||||
|
|
|
|||
|
|
@ -49,7 +49,7 @@ class IsohuntBackend(BaseBackend, ICapTorrent):
|
|||
return self.browser.openurl(torrent.url.encode('utf-8')).read()
|
||||
|
||||
def iter_torrents(self, pattern):
|
||||
return self.browser.iter_torrents(pattern.replace(' ','+'))
|
||||
return self.browser.iter_torrents(pattern.replace(' ', '+'))
|
||||
|
||||
def fill_torrent(self, torrent, fields):
|
||||
if 'description' in fields or 'files' in fields:
|
||||
|
|
@ -61,5 +61,5 @@ class IsohuntBackend(BaseBackend, ICapTorrent):
|
|||
return torrent
|
||||
|
||||
OBJECTS = {
|
||||
Torrent:fill_torrent
|
||||
Torrent: fill_torrent
|
||||
}
|
||||
|
|
|
|||
|
|
@ -32,9 +32,9 @@ class IsohuntBrowser(BaseBrowser):
|
|||
ENCODING = 'utf-8'
|
||||
USER_AGENT = BaseBrowser.USER_AGENTS['wget']
|
||||
PAGES = {
|
||||
'https://isohunt.com/torrents/.*iht=-1&ihp=1&ihs1=1&iho1=d' : TorrentsPage,
|
||||
'https://isohunt.com/torrent_details.*tab=summary' : TorrentPage,
|
||||
}
|
||||
'https://isohunt.com/torrents/.*iht=-1&ihp=1&ihs1=1&iho1=d': TorrentsPage,
|
||||
'https://isohunt.com/torrent_details.*tab=summary': TorrentPage,
|
||||
}
|
||||
|
||||
def home(self):
|
||||
return self.location('https://isohunt.com')
|
||||
|
|
|
|||
|
|
@ -73,7 +73,8 @@ class TorrentPage(BasePage):
|
|||
title = NotAvailable
|
||||
size = NotAvailable
|
||||
url = 'https://isohunt.com/download/%s/%s.torrent' % (id, id)
|
||||
title = unicode(self.parser.select(self.document.getroot(),'head > meta[name=title]',1).attrib.get('content',''))
|
||||
title = unicode(self.parser.select(
|
||||
self.document.getroot(), 'head > meta[name=title]', 1).attrib.get('content', ''))
|
||||
seed = NotAvailable
|
||||
leech = NotAvailable
|
||||
tip_id = "none"
|
||||
|
|
|
|||
|
|
@ -72,5 +72,5 @@ class KickassBackend(BaseBackend, ICapTorrent):
|
|||
return torrent
|
||||
|
||||
OBJECTS = {
|
||||
Torrent:fill_torrent
|
||||
Torrent: fill_torrent
|
||||
}
|
||||
|
|
|
|||
|
|
@ -34,7 +34,7 @@ class KickassBrowser(BaseBrowser):
|
|||
PAGES = {
|
||||
'http://kat.ph/usearch/.*field=seeders&sorder=desc': TorrentsPage,
|
||||
'http://kat.ph/.*.html': TorrentPage,
|
||||
}
|
||||
}
|
||||
|
||||
def home(self):
|
||||
return self.location('http://kat.ph')
|
||||
|
|
|
|||
|
|
@ -31,7 +31,7 @@ from weboob.tools.browser import BasePage
|
|||
from weboob.tools.misc import get_bytes_size
|
||||
|
||||
|
||||
__all__ = ['TorrentsPage','TorrentPage']
|
||||
__all__ = ['TorrentsPage', 'TorrentPage']
|
||||
|
||||
|
||||
class TorrentsPage(BasePage):
|
||||
|
|
@ -53,14 +53,14 @@ class TorrentsPage(BasePage):
|
|||
.replace('.html', '')
|
||||
|
||||
# look for url
|
||||
for a in self.parser.select(tr,'div.iaconbox a'):
|
||||
for a in self.parser.select(tr, 'div.iaconbox a'):
|
||||
href = a.attrib.get('href', '')
|
||||
if href.startswith('magnet'):
|
||||
magnet = unicode(href)
|
||||
elif href.startswith('http'):
|
||||
url = unicode(href)
|
||||
elif href.startswith('//'):
|
||||
url = u'http:%s'%href
|
||||
url = u'http:%s' % href
|
||||
|
||||
size = tr.getchildren()[1].text
|
||||
u = tr.getchildren()[1].getchildren()[0].text
|
||||
|
|
@ -107,16 +107,16 @@ class TorrentPage(BasePage):
|
|||
leech = 0
|
||||
|
||||
title = self.parser.select(self.document.getroot(),
|
||||
'h1.torrentName span', 1)
|
||||
'h1.torrentName span', 1)
|
||||
title = unicode(title.text)
|
||||
|
||||
for a in self.parser.select(self.document.getroot(),
|
||||
'div.downloadButtonGroup a'):
|
||||
'div.downloadButtonGroup a'):
|
||||
href = a.attrib.get('href', '')
|
||||
if href.startswith('magnet'):
|
||||
magnet = unicode(href)
|
||||
elif href.startswith('//'):
|
||||
url = u'http:%s'%href
|
||||
url = u'http:%s' % href
|
||||
elif href.startswith('http'):
|
||||
url = unicode(href)
|
||||
|
||||
|
|
@ -127,7 +127,7 @@ class TorrentPage(BasePage):
|
|||
# is enough to know if this is the right span
|
||||
if (span.attrib.get('class', '') == 'folder'
|
||||
or span.attrib.get('class', '') == 'folderopen') \
|
||||
and len(span.getchildren()) > 2:
|
||||
and len(span.getchildren()) > 2:
|
||||
size = span.getchildren()[1].tail
|
||||
u = span.getchildren()[2].text
|
||||
size = float(size.split(': ')[1].replace(',', '.'))
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@
|
|||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
from weboob.capabilities.recipe import ICapRecipe,Recipe
|
||||
from weboob.capabilities.recipe import ICapRecipe, Recipe
|
||||
from weboob.tools.backend import BaseBackend
|
||||
|
||||
from .browser import MarmitonBrowser
|
||||
|
|
@ -48,16 +48,16 @@ class MarmitonBackend(BaseBackend, ICapRecipe):
|
|||
def fill_recipe(self, recipe, fields):
|
||||
if 'nb_person' in fields or 'instructions' in fields:
|
||||
rec = self.get_recipe(recipe.id)
|
||||
recipe.picture_url = rec.picture_url
|
||||
recipe.instructions = rec.instructions
|
||||
recipe.ingredients = rec.ingredients
|
||||
recipe.comments = rec.comments
|
||||
recipe.nb_person = rec.nb_person
|
||||
recipe.cooking_time = rec.cooking_time
|
||||
recipe.picture_url = rec.picture_url
|
||||
recipe.instructions = rec.instructions
|
||||
recipe.ingredients = rec.ingredients
|
||||
recipe.comments = rec.comments
|
||||
recipe.nb_person = rec.nb_person
|
||||
recipe.cooking_time = rec.cooking_time
|
||||
recipe.preparation_time = rec.preparation_time
|
||||
|
||||
return recipe
|
||||
|
||||
OBJECTS = {
|
||||
Recipe:fill_recipe,
|
||||
}
|
||||
Recipe: fill_recipe,
|
||||
}
|
||||
|
|
|
|||
|
|
@ -34,7 +34,7 @@ class MarmitonBrowser(BaseBrowser):
|
|||
PAGES = {
|
||||
'http://www.marmiton.org/recettes/recherche.aspx.*': ResultsPage,
|
||||
'http://www.marmiton.org/recettes/recette_.*': RecipePage,
|
||||
}
|
||||
}
|
||||
|
||||
def iter_recipes(self, pattern):
|
||||
self.location('http://www.marmiton.org/recettes/recherche.aspx?st=5&cli=1&aqt=%s' % (pattern))
|
||||
|
|
|
|||
|
|
@ -30,27 +30,28 @@ class ResultsPage(BasePage):
|
|||
""" Page which contains results as a list of recipies
|
||||
"""
|
||||
def iter_recipes(self):
|
||||
for div in self.parser.select(self.document.getroot(),'div.m_search_result'):
|
||||
tds = self.parser.select(div,'td')
|
||||
for div in self.parser.select(self.document.getroot(), 'div.m_search_result'):
|
||||
tds = self.parser.select(div, 'td')
|
||||
if len(tds) == 2:
|
||||
title = NotAvailable
|
||||
thumbnail_url = NotAvailable
|
||||
short_description = NotAvailable
|
||||
imgs = self.parser.select(tds[0],'img')
|
||||
imgs = self.parser.select(tds[0], 'img')
|
||||
if len(imgs) > 0:
|
||||
thumbnail_url = unicode(imgs[0].attrib.get('src',''))
|
||||
link = self.parser.select(tds[1],'div.m_search_titre_recette a',1)
|
||||
thumbnail_url = unicode(imgs[0].attrib.get('src', ''))
|
||||
link = self.parser.select(tds[1], 'div.m_search_titre_recette a', 1)
|
||||
title = unicode(link.text)
|
||||
id = link.attrib.get('href','').replace('.aspx','').replace('/recettes/recette_','')
|
||||
short_description = unicode(' '.join(self.parser.select(tds[1],'div.m_search_result_part4',1).text.strip().split('\n')))
|
||||
id = link.attrib.get('href', '').replace('.aspx', '').replace('/recettes/recette_', '')
|
||||
short_description = unicode(' '.join(self.parser.select(tds[
|
||||
1], 'div.m_search_result_part4', 1).text.strip().split('\n')))
|
||||
|
||||
recipe = Recipe(id,title)
|
||||
recipe = Recipe(id, title)
|
||||
recipe.thumbnail_url = thumbnail_url
|
||||
recipe.short_description= short_description
|
||||
recipe.instructions = NotLoaded
|
||||
recipe.ingredients = NotLoaded
|
||||
recipe.nb_person = NotLoaded
|
||||
recipe.cooking_time = NotLoaded
|
||||
recipe.short_description = short_description
|
||||
recipe.instructions = NotLoaded
|
||||
recipe.ingredients = NotLoaded
|
||||
recipe.nb_person = NotLoaded
|
||||
recipe.cooking_time = NotLoaded
|
||||
recipe.preparation_time = NotLoaded
|
||||
yield recipe
|
||||
|
||||
|
|
@ -68,30 +69,30 @@ class RecipePage(BasePage):
|
|||
instructions = NotAvailable
|
||||
comments = []
|
||||
|
||||
title = unicode(self.parser.select(self.document.getroot(),'h1.m_title',1).text_content().strip())
|
||||
main = self.parser.select(self.document.getroot(),'div.m_content_recette_main',1)
|
||||
preparation_time = int(self.parser.select(main,'p.m_content_recette_info span.preptime',1).text_content())
|
||||
cooking_time = int(self.parser.select(main,'p.m_content_recette_info span.cooktime',1).text_content())
|
||||
ing_header_line = self.parser.select(main,'p.m_content_recette_ingredients span',1).text_content()
|
||||
title = unicode(self.parser.select(self.document.getroot(), 'h1.m_title', 1).text_content().strip())
|
||||
main = self.parser.select(self.document.getroot(), 'div.m_content_recette_main', 1)
|
||||
preparation_time = int(self.parser.select(main, 'p.m_content_recette_info span.preptime', 1).text_content())
|
||||
cooking_time = int(self.parser.select(main, 'p.m_content_recette_info span.cooktime', 1).text_content())
|
||||
ing_header_line = self.parser.select(main, 'p.m_content_recette_ingredients span', 1).text_content()
|
||||
if '(pour' in ing_header_line and ')' in ing_header_line:
|
||||
nb_person = int(ing_header_line.split('pour ')[-1].split('personnes)')[0].split()[0])
|
||||
ingredients = self.parser.select(main,'p.m_content_recette_ingredients',1).text_content().strip().split('- ')
|
||||
ingredients=ingredients[1:]
|
||||
rinstructions = self.parser.select(main,'div.m_content_recette_todo',1).text_content().strip()
|
||||
ingredients = self.parser.select(main, 'p.m_content_recette_ingredients', 1).text_content().strip().split('- ')
|
||||
ingredients = ingredients[1:]
|
||||
rinstructions = self.parser.select(main, 'div.m_content_recette_todo', 1).text_content().strip()
|
||||
instructions = u''
|
||||
for line in rinstructions.split('\n'):
|
||||
instructions += '%s\n'%line.strip()
|
||||
instructions += '%s\n' % line.strip()
|
||||
instructions = instructions.strip('\n')
|
||||
imgillu = self.parser.select(self.document.getroot(),'a.m_content_recette_illu img')
|
||||
imgillu = self.parser.select(self.document.getroot(), 'a.m_content_recette_illu img')
|
||||
if len(imgillu) > 0:
|
||||
picture_url = unicode(imgillu[0].attrib.get('src',''))
|
||||
for divcom in self.parser.select(self.document.getroot(),'div.m_commentaire_row'):
|
||||
note = self.parser.select(divcom,'div.m_commentaire_note span',1).text.strip()
|
||||
user = self.parser.select(divcom,'div.m_commentaire_content span',1).text.strip()
|
||||
content = self.parser.select(divcom,'div.m_commentaire_content p',1).text.strip()
|
||||
comments.append(u'user: %s, note: %s, comment: %s'%(user,note,content))
|
||||
picture_url = unicode(imgillu[0].attrib.get('src', ''))
|
||||
for divcom in self.parser.select(self.document.getroot(), 'div.m_commentaire_row'):
|
||||
note = self.parser.select(divcom, 'div.m_commentaire_note span', 1).text.strip()
|
||||
user = self.parser.select(divcom, 'div.m_commentaire_content span', 1).text.strip()
|
||||
content = self.parser.select(divcom, 'div.m_commentaire_content p', 1).text.strip()
|
||||
comments.append(u'user: %s, note: %s, comment: %s' % (user, note, content))
|
||||
|
||||
recipe = Recipe(id,title)
|
||||
recipe = Recipe(id, title)
|
||||
recipe.preparation_time = preparation_time
|
||||
recipe.cooking_time = cooking_time
|
||||
recipe.nb_person = nb_person
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@
|
|||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
from weboob.capabilities.subtitle import ICapSubtitle,LanguageNotSupported,Subtitle
|
||||
from weboob.capabilities.subtitle import ICapSubtitle, LanguageNotSupported, Subtitle
|
||||
from weboob.applications.suboob.suboob import LANGUAGE_CONV
|
||||
from weboob.tools.backend import BaseBackend
|
||||
|
||||
|
|
@ -53,15 +53,15 @@ class OpensubtitlesBackend(BaseBackend, ICapSubtitle):
|
|||
def iter_subtitles(self, language, pattern):
|
||||
if language not in LANGUAGE_CONV.keys():
|
||||
raise LanguageNotSupported()
|
||||
return self.browser.iter_subtitles(language,quote_plus(pattern.encode('utf-8')))
|
||||
return self.browser.iter_subtitles(language, quote_plus(pattern.encode('utf-8')))
|
||||
|
||||
def fill_subtitle(self, subtitle, fields):
|
||||
if 'description' in fields:
|
||||
sub = self.get_subtitle(subtitle.id)
|
||||
subtitle.description = sub.description
|
||||
subtitle.description = sub.description
|
||||
|
||||
return subtitle
|
||||
|
||||
OBJECTS = {
|
||||
Subtitle:fill_subtitle,
|
||||
}
|
||||
Subtitle: fill_subtitle,
|
||||
}
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Reference in a new issue