Add --list-extractor-descriptions (human-readable list of IEs)

This commit is contained in:
Philipp Hagemeister 2013-07-01 18:52:19 +02:00
parent 2db67bc0f4
commit 0f81866329
9 changed files with 34 additions and 22 deletions

View file

@ -35,6 +35,7 @@
import getpass
import optparse
import os
import random
import re
import shlex
import socket
@ -142,6 +143,9 @@ def _find_term_columns():
general.add_option('--list-extractors',
action='store_true', dest='list_extractors',
help='List all supported extractors and the URLs they would handle', default=False)
general.add_option('--list-extractor-descriptions',
action='store_true', dest='list_extractor_descriptions',
help='Output descriptions of all supported extractors', default=False)
general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
@ -427,6 +431,18 @@ def _real_main(argv=None):
for mu in matchedUrls:
compat_print(u' ' + mu)
sys.exit(0)
if opts.list_extractor_descriptions:
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
if not ie._WORKING:
continue
desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
if hasattr(ie, 'SEARCH_KEY'):
_SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise')
_COUNTS = (u'', u'5', u'10', u'all')
desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
compat_print(desc)
sys.exit(0)
# Conflicting, missing and erroneous options
if opts.usenetrc and (opts.username is not None or opts.password is not None):

View file

@ -12,8 +12,7 @@
class ComedyCentralIE(InfoExtractor):
"""Information extractor for The Daily Show and Colbert Report """
IE_DESC = u'The Daily Show / Colbert Report'
# urls can be abbreviations like :thedailyshow or :colbert
# urls for episodes like:
# or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day

View file

@ -263,3 +263,7 @@ def _real_extract(self, query):
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
raise NotImplementedError("This method must be implemented by sublclasses")
@property
def SEARCH_KEY(self):
return self._SEARCH_KEY

View file

@ -11,8 +11,7 @@
)
class GenericIE(InfoExtractor):
"""Generic last-resort information extractor."""
IE_DESC = u'Generic downloader that works on some sites'
_VALID_URL = r'.*'
IE_NAME = u'generic'
_TEST = {

View file

@ -10,8 +10,7 @@
class GooglePlusIE(InfoExtractor):
"""Information extractor for plus.google.com."""
IE_DESC = u'Google Plus'
_VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
IE_NAME = u'plus.google'
_TEST = {

View file

@ -8,7 +8,7 @@
class GoogleSearchIE(SearchInfoExtractor):
"""Information Extractor for Google Video search queries."""
IE_DESC = u'Google Video search'
_MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
_MAX_RESULTS = 1000
IE_NAME = u'video.google:search'

View file

@ -16,10 +16,9 @@
class StanfordOpenClassroomIE(InfoExtractor):
"""Information extractor for Stanford's Open ClassRoom"""
_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
IE_NAME = u'stanfordoc'
IE_DESC = u'Stanford Open ClassRoom'
_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
_TEST = {
u'url': u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
u'file': u'PracticalUnix_intro-environment.mp4',

View file

@ -11,7 +11,7 @@
)
class YahooIE(InfoExtractor):
"""Information extractor for screen.yahoo.com."""
IE_DESC = u'Yahoo screen'
_VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
_TEST = {
u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
@ -88,8 +88,7 @@ def _real_extract(self, url):
return info_dict
class YahooSearchIE(SearchInfoExtractor):
"""Information Extractor for Yahoo! Video search queries."""
IE_DESC = u'Yahoo screen search'
_MAX_RESULTS = 1000
IE_NAME = u'screen.yahoo:search'
_SEARCH_KEY = 'yvsearch'

View file

@ -23,8 +23,7 @@
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
IE_DESC = u'YouTube.com'
_VALID_URL = r"""^
(
(?:https?://)? # http(s):// (optional)
@ -629,8 +628,7 @@ def _real_extract(self, url):
return results
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
IE_DESC = u'YouTube.com playlists'
_VALID_URL = r"""(?:
(?:https?://)?
(?:\w+\.)?
@ -697,8 +695,7 @@ def _real_extract(self, url):
class YoutubeChannelIE(InfoExtractor):
"""Information Extractor for YouTube channels."""
IE_DESC = u'YouTube.com channels'
_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"
_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
_MORE_PAGES_INDICATOR = 'yt-uix-load-more'
@ -756,8 +753,7 @@ def _real_extract(self, url):
class YoutubeUserIE(InfoExtractor):
"""Information Extractor for YouTube users."""
IE_DESC = u'YouTube.com user videos (URL or "ytuser" keyword)'
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
_GDATA_PAGE_SIZE = 50
@ -813,7 +809,7 @@ def _real_extract(self, url):
return [self.playlist_result(url_results, playlist_title = username)]
class YoutubeSearchIE(SearchInfoExtractor):
"""Information Extractor for YouTube search queries."""
IE_DESC = u'YouTube.com searches'
_API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
_MAX_RESULTS = 1000
IE_NAME = u'youtube:search'
@ -856,6 +852,7 @@ def _get_n_results(self, query, n):
class YoutubeShowIE(InfoExtractor):
IE_DESC = u'YouTube.com (multi-season) shows'
_VALID_URL = r'https?://www\.youtube\.com/show/(.*)'
IE_NAME = u'youtube:show'