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

imdb in progress...

Browse source
This commit is contained in:
Julien Veyssier 2013-03-04 05:06:31 +01:00
commit a82483727b
4 changed files with 62 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

64
modules/imdb/pages.py
View file

@ -33,7 +33,8 @@ class MoviePage(BasePage):
def get_movie(self,id):
title = NotAvailable
duration = NotAvailable
description = NotAvailable.__unicode__()
release_date = NotAvailable
description = NotAvailable
td_overview = self.parser.select(self.document.getroot(),'td#overview-top',1)
for span in self.parser.select(td_overview,'h1.header span[itemprop=name]'):
if span.attrib.get('class','') == 'itemprop':
@ -42,10 +43,12 @@ class MoviePage(BasePage):
title = other_titles
elif span.attrib.get('class','') == 'title-extra':
title = span.text
meta = self.parser.select(td_overview,'meta[itemprop=datePublished]',1)
datestrings = meta.attrib.get('content','').split('-')
if len(datestrings) == 2:
datestrings.append('1')
metas = self.parser.select(td_overview,'meta[itemprop=datePublished]')
if len(metas) > 0:
datestrings = metas[0].attrib.get('content','').split('-')
if len(datestrings) == 2:
datestrings.append('1')
release_date = datetime(int(datestrings[0]),int(datestrings[1]),int(datestrings[2]))
time = self.parser.select(td_overview,'time[itemprop=duration]')
if len(time) > 0:
duration = int(time[0].attrib.get('datetime','').strip(string.letters))
@ -54,7 +57,7 @@ class MoviePage(BasePage):
description = desc[0].text
movie = Movie(id,title.strip())
movie.other_titles = other_titles.strip()
movie.release_date = datetime(int(datestrings[0]),int(datestrings[1]),int(datestrings[2]))
movie.release_date = release_date
movie.duration = duration
movie.description = description
movie.note = "10/10"
@ -81,22 +84,55 @@ class MovieCrewPage(BasePage):
person.real_name = NotAvailable
person.birth_date = NotAvailable
person.nationality = NotAvailable
person.biography = NotAvailable
person.gender = NotAvailable
yield person
class PersonPage(BasePage):
def get_person(self,id):
person = Person(id,'nameplop')
person.real_name = 'rn'
person.birth_date = datetime.now()
person.birth_place = "place"
person.gender = "M"
person.nationality = "nn"
person.biography = 'bio'
name = NotAvailable
biography = NotAvailable
birth_place = NotAvailable
birth_date = NotAvailable
real_name = NotAvailable
gender = NotAvailable
nationality = NotAvailable
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:
biography = descs[0].text
names = self.parser.select(td_overview,'h1[itemprop=name]')
if len(names) > 0:
name = names[0].text
times = self.parser.select(td_overview,'time[itemprop=birthDate]')
if len(times) > 0:
time = times[0].attrib.get('datetime','').split('-')
birth_date = datetime(int(time[0]),int(time[1]),int(time[2]))
person = Person(id,name)
person.real_name = real_name
person.birth_date = birth_date
person.birth_place = birth_place
person.gender = gender
person.nationality = nationality
person.biography = biography
person.awards = ["aw1","aw2"]
person.roles = {}
return person
def iter_movies(self,person_id):
pass
for movie_div in self.parser.select(self.document.getroot(),'div[class~=filmo-row]'):
a = self.parser.select(movie_div,'b a',1)
id = a.attrib.get('href','').strip('/').split('/')[-1]
yield self.browser.get_movie(id)
#title = a.text
#movie = Movie(id,title)
#movie.other_titles = NotAvailable
#movie.release_date = NotAvailable
#movie.duration = NotAvailable
#movie.description = NotAvailable
#movie.note = NotAvailable
#movie.awards = NotAvailable
#movie.roles = NotAvailable
#yield movie