dinislage/CouchPotatoServer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Get full imdb (watch)list without login. fix #2715

Browse Source
This commit is contained in:
Ruud
2014-01-22 23:38:18 +01:00
parent ca94d48f8b
commit 52c64c1a6a
2 changed files with 43 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
couchpotato/core/providers/automation/imdb/__init__.py
+1 -1
View File
@@ -12,7 +12,7 @@ config = [{
'list': 'watchlist_providers',
'name': 'imdb_automation_watchlist',
'label': 'IMDB',
'description': 'From any <strong>public</strong> IMDB watchlists. Url should be the CSV link.',
'description': 'From any <strong>public</strong> IMDB watchlists.',
'options': [
{
'name': 'automation_enabled',
couchpotato/core/providers/automation/imdb/main.py
+42 -9
View File
@@ -1,4 +1,5 @@
import traceback
import re
from bs4 import BeautifulSoup
from couchpotato import fireEvent
@@ -42,23 +43,55 @@ class IMDBWatchlist(IMDBBase):
index = -1
for watchlist_url in watchlist_urls:
try:
# Get list ID
ids = re.findall('[list/|list_id=]([a-zA-Z0-9\-_]{11})', watchlist_url)
if len(ids) == 1:
watchlist_url = 'http://www.imdb.com/list/%s/?view=compact&sort=created:asc' % ids[0]
# Try find user id with watchlist
else:
userids = re.findall('(ur\d{7})', watchlist_url)
if len(userids) == 1:
watchlist_url = 'http://www.imdb.com/user/%s/watchlist?view=compact&sort=created:asc' % userids[0]
except:
log.error('Failed getting id from watchlist: %s', traceback.format_exc())
index += 1
if not watchlist_enablers[index]:
continue
try:
log.debug('Started IMDB watchlists: %s', watchlist_url)
rss_data = self.getHTMLData(watchlist_url)
imdbs = getImdb(rss_data, multiple = True) if rss_data else []
start = 0
while True:
try:
for imdb in imdbs:
movies.append(imdb)
w_url = '%s&start=%s' % (watchlist_url, start)
log.debug('Started IMDB watchlists: %s', w_url)
html = self.getHTMLData(w_url)
if self.shuttingDown():
try:
split = splitString(html, split_on="<div class=\"list compact\">")[1]
html = splitString(split, split_on="<div class=\"pages\">")[0]
except:
pass
imdbs = getImdb(html, multiple = True) if html else []
for imdb in imdbs:
if imdb not in movies:
movies.append(imdb)
if self.shuttingDown():
break
log.debug('Found %s movies on %s', (len(imdbs), w_url))
if len(imdbs) < 250:
break
except:
log.error('Failed loading IMDB watchlist: %s %s', (watchlist_url, traceback.format_exc()))
start += 250
except:
log.error('Failed loading IMDB watchlist: %s %s', (watchlist_url, traceback.format_exc()))
return movies