R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

replaced tabs with spaces in moviestorm IE

Browse Source
This commit is contained in:
Philip Ardery 2015-03-14 14:53:41 -04:00
parent 8654a8484f
commit 0dc602d9e3
1 changed files with 23 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
youtube_dl/extractor/moviestorm.py
View File

@ -56,13 +56,13 @@ class MovieStormIE(InfoExtractor):
_VALID_URL = r'http://moviestorm\.eu/view/(\d+)-watch-(.*)/season-(\d+)/episode-(\d+)' _VALID_URL = r'http://moviestorm\.eu/view/(\d+)-watch-(.*)/season-(\d+)/episode-(\d+)'
_LINK_FARM = True _LINK_FARM = True
# There are no tests for this IE because the links on any given moviestorm # There are no tests for this IE because the links on any given moviestorm
# page can dynamically change, and because the actual download/extraction # page can dynamically change, and because the actual download/extraction
# is ultimately preformed by another IE. An example of an acceptable url to # is ultimately preformed by another IE. An example of an acceptable url to
# feed to this IE is: http://moviestorm.eu/view/218-watch-the-simpsons/season-26/episode-1 # feed to this IE is: http://moviestorm.eu/view/218-watch-the-simpsons/season-26/episode-1
_TEST = False _TEST = False
# moviestorm's drupal db config is unstable at times # moviestorm's drupal db config is unstable at times
# retry up to 5 times before giving up, 5 second delay # retry up to 5 times before giving up, 5 second delay
# between each retry # between each retry
retry_count = 0 retry_count = 0
@ -79,12 +79,12 @@ class MovieStormIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
# retry loop to capture moviestorm page # retry loop to capture moviestorm page
while True: while True:
if self.retry_count == 0: if self.retry_count == 0:
note = 'Downloading link farm page' note = 'Downloading link farm page'
else: else:
note = ('Unstable db connection, retying again in %s seconds ' note = ('Unstable db connection, retying again in %s seconds '
'[%s/%s]' % (self.retry_wait, self.retry_count, '[%s/%s]' % (self.retry_wait, self.retry_count,
self.max_retries)) self.max_retries))
(_, _, token) = self._parse_target(url) (_, _, token) = self._parse_target(url)
farmpage = self._download_webpage( farmpage = self._download_webpage(
@ -95,14 +95,14 @@ class MovieStormIE(InfoExtractor):
) )
if farmpage.strip() != 'MySQL server has gone away': if farmpage.strip() != 'MySQL server has gone away':
break break
if self.retry_count < self.max_retries: if self.retry_count < self.max_retries:
self.retry_count += 1 self.retry_count += 1
sleep(self.retry_wait) sleep(self.retry_wait)
else: else:
msg = 'The moviestorm database is currently unstable. Please try again later.' msg = 'The moviestorm database is currently unstable. Please try again later.'
raise ExtractorError(msg, expected=True) raise ExtractorError(msg, expected=True)
# scrape WATCH button links from moviestorm page # scrape WATCH button links from moviestorm page
self.to_screen(': Extracting watch page urls') self.to_screen(': Extracting watch page urls')
@ -111,18 +111,18 @@ class MovieStormIE(InfoExtractor):
# get direct urls from scraped watch pages # get direct urls from scraped watch pages
self.to_screen(': Extracting direct links from watch pages') self.to_screen(': Extracting direct links from watch pages')
for watch_url in watch_urls: for watch_url in watch_urls:
(_, _, token) = self._parse_target(watch_url) (_, _, token) = self._parse_target(watch_url)
watchpage = self._download_webpage( watchpage = self._download_webpage(
watch_url, token, watch_url, token,
note=False, note=False,
errnote='Unable to download link farm watch page', errnote='Unable to download link farm watch page',
fatal=False fatal=False
) )
if watchpage is not None: if watchpage is not None:
direct_url = MovieStormHTMLParser.extract_direct_url(watchpage) direct_url = MovieStormHTMLParser.extract_direct_url(watchpage)
if direct_url: if direct_url:
self.direct_urls.append(direct_url) self.direct_urls.append(direct_url)
self.to_screen(': Passing off farmed links to InfoExtractors') self.to_screen(': Passing off farmed links to InfoExtractors')
return list(set(self.direct_urls)) return list(set(self.direct_urls))