2014-08-15 07:38:41 -07:00
from __future__ import unicode_literals
from . common import InfoExtractor
2014-12-11 19:23:34 -08:00
from . . utils import (
find_xpath_attr ,
int_or_none ,
js_to_json ,
unescapeHTML ,
2016-03-31 13:09:27 -07:00
determine_ext ,
2014-12-11 19:23:34 -08:00
)
2014-08-15 07:38:41 -07:00
class HowStuffWorksIE ( InfoExtractor ) :
2015-07-17 08:45:53 -07:00
_VALID_URL = r ' https?://[ \ da-z-]+ \ .howstuffworks \ .com/(?:[^/]+/)*(?: \ d+-)?(?P<id>.+?)-video \ .htm '
2014-08-15 07:38:41 -07:00
_TESTS = [
{
2014-12-05 10:46:49 -08:00
' url ' : ' http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm ' ,
2014-08-15 07:38:41 -07:00
' info_dict ' : {
2014-12-05 10:46:49 -08:00
' id ' : ' 450221 ' ,
' ext ' : ' flv ' ,
' title ' : ' Cool Jobs - Iditarod Musher ' ,
' description ' : ' Cold sleds, freezing temps and warm dog breath... an Iditarod musher \' s dream. Kasey-Dee Gardner jumps on a sled to find out what the big deal is. ' ,
2014-12-11 19:23:34 -08:00
' display_id ' : ' cool-jobs-iditarod-musher ' ,
' thumbnail ' : ' re:^https?://.* \ .jpg$ ' ,
' duration ' : 161 ,
2014-08-15 07:38:41 -07:00
} ,
} ,
{
2014-10-11 03:29:42 -07:00
' url ' : ' http://adventure.howstuffworks.com/7199-survival-zone-food-and-water-in-the-savanna-video.htm ' ,
2014-08-15 07:38:41 -07:00
' info_dict ' : {
2014-10-11 03:29:42 -07:00
' id ' : ' 453464 ' ,
2014-08-15 07:38:41 -07:00
' ext ' : ' mp4 ' ,
2014-10-11 03:29:42 -07:00
' title ' : ' Survival Zone: Food and Water In the Savanna ' ,
2014-12-04 15:09:17 -08:00
' description ' : ' Learn how to find both food and water while trekking in the African savannah. In this video from the Discovery Channel. ' ,
2014-12-11 19:23:34 -08:00
' display_id ' : ' survival-zone-food-and-water-in-the-savanna ' ,
' thumbnail ' : ' re:^https?://.* \ .jpg$ ' ,
2014-08-15 07:38:41 -07:00
} ,
} ,
{
2014-12-05 10:46:49 -08:00
' url ' : ' http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm ' ,
2014-08-15 07:38:41 -07:00
' info_dict ' : {
2014-12-05 10:46:49 -08:00
' id ' : ' 440011 ' ,
2016-03-31 13:09:27 -07:00
' ext ' : ' mp4 ' ,
2014-12-05 10:46:49 -08:00
' title ' : ' Sword Swallowing #1 by Dan Meyer ' ,
' description ' : ' Video footage (1 of 3) used by permission of the owner Dan Meyer through Sword Swallowers Association International <www.swordswallow.org> ' ,
2014-12-11 19:23:34 -08:00
' display_id ' : ' sword-swallowing-1-by-dan-meyer ' ,
' thumbnail ' : ' re:^https?://.* \ .jpg$ ' ,
2014-08-15 07:38:41 -07:00
} ,
} ,
2015-07-17 08:43:27 -07:00
{
' url ' : ' http://shows.howstuffworks.com/stuff-to-blow-your-mind/optical-illusions-video.htm ' ,
2015-07-17 09:07:55 -07:00
' only_matching ' : True ,
2015-07-17 08:43:27 -07:00
}
2014-08-15 07:38:41 -07:00
]
def _real_extract ( self , url ) :
2014-12-04 15:09:17 -08:00
display_id = self . _match_id ( url )
2014-08-15 07:38:41 -07:00
webpage = self . _download_webpage ( url , display_id )
2014-12-11 19:23:34 -08:00
clip_js = self . _search_regex (
r ' (?s)var clip = ( { .*?}); ' , webpage , ' clip info ' )
clip_info = self . _parse_json (
clip_js , display_id , transform_source = js_to_json )
2014-12-05 10:46:49 -08:00
2014-12-11 19:23:34 -08:00
video_id = clip_info [ ' content_id ' ]
2014-08-15 07:38:41 -07:00
formats = [ ]
2014-12-11 19:23:34 -08:00
m3u8_url = clip_info . get ( ' m3u8 ' )
2016-03-31 13:09:27 -07:00
if m3u8_url and determine_ext ( m3u8_url ) == ' m3u8 ' :
formats . extend ( self . _extract_m3u8_formats ( m3u8_url , video_id , ' mp4 ' , format_id = ' hls ' , fatal = True ) )
flv_url = clip_info . get ( ' flv_url ' )
if flv_url :
formats . append ( {
' url ' : flv_url ,
' format_id ' : ' flv ' ,
} )
2014-12-11 19:23:34 -08:00
for video in clip_info . get ( ' mp4 ' , [ ] ) :
2014-12-04 15:09:17 -08:00
formats . append ( {
' url ' : video [ ' src ' ] ,
2016-03-31 13:09:27 -07:00
' format_id ' : ' mp4- %s ' % video [ ' bitrate ' ] ,
' vbr ' : int_or_none ( video [ ' bitrate ' ] . rstrip ( ' k ' ) ) ,
2014-12-04 15:09:17 -08:00
} )
2014-12-05 10:46:49 -08:00
if not formats :
smil = self . _download_xml (
' http://services.media.howstuffworks.com/videos/ %s /smil-service.smil ' % video_id ,
video_id , ' Downloading video SMIL ' )
http_base = find_xpath_attr (
smil ,
' ./ {0} head/ {0} meta ' . format ( ' { http://www.w3.org/2001/SMIL20/Language} ' ) ,
' name ' ,
' httpBase ' ) . get ( ' content ' )
URL_SUFFIX = ' ?v=2.11.3&fp=LNX 11,2,202,356&r=A&g=A '
for video in smil . findall (
' ./ {0} body/ {0} switch/ {0} video ' . format ( ' { http://www.w3.org/2001/SMIL20/Language} ' ) ) :
2014-12-11 19:23:34 -08:00
vbr = int_or_none ( video . attrib [ ' system-bitrate ' ] , scale = 1000 )
2014-12-05 10:46:49 -08:00
formats . append ( {
' url ' : ' %s / %s %s ' % ( http_base , video . attrib [ ' src ' ] , URL_SUFFIX ) ,
' format_id ' : ' %d k ' % vbr ,
' vbr ' : vbr ,
} )
2014-08-15 07:38:41 -07:00
self . _sort_formats ( formats )
return {
2014-12-11 19:23:34 -08:00
' id ' : ' %s ' % video_id ,
2014-08-15 07:38:41 -07:00
' display_id ' : display_id ,
2014-12-11 19:23:34 -08:00
' title ' : unescapeHTML ( clip_info [ ' clip_title ' ] ) ,
' description ' : unescapeHTML ( clip_info . get ( ' caption ' ) ) ,
' thumbnail ' : clip_info . get ( ' video_still_url ' ) ,
2016-03-31 13:09:27 -07:00
' duration ' : int_or_none ( clip_info . get ( ' duration ' ) ) ,
2014-08-15 07:38:41 -07:00
' formats ' : formats ,
}