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

reuters: fix syntax

Browse Source
This commit is contained in:
fnord 2015-07-17 03:27:47 -05:00
parent 1ee382603f
commit d4ebd851ef
1 changed files with 77 additions and 81 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/extractor/yospace.py
View File

@ -4,14 +4,12 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
parse_iso8601, ExtractorError,
strip_jsonp,
js_to_json, js_to_json,
float_or_none, float_or_none,
int_or_none, int_or_none,
) )
import re
from pprint import pprint
class YospaceIE(InfoExtractor): class YospaceIE(InfoExtractor):
_VALID_URL = r'http://(?:csm-[a-z]|mas-[a-z]).cds\d+.yospace.com/(?P<type>csm|mas)/(?P<id>\d+/\d+)' _VALID_URL = r'http://(?:csm-[a-z]|mas-[a-z]).cds\d+.yospace.com/(?P<type>csm|mas)/(?P<id>\d+/\d+)'
@ -64,7 +62,6 @@ class YospaceIE(InfoExtractor):
video_id = mobj.group('id') video_id = mobj.group('id')
url_type = mobj.group('type') url_type = mobj.group('type')
display_id = url_type display_id = url_type
title = display_id
formats = [] formats = []
hls_url = None hls_url = None
@ -77,7 +74,6 @@ class YospaceIE(InfoExtractor):
if hls_url is not None: if hls_url is not None:
formats.extend(self._extract_m3u8(hls_url)) formats.extend(self._extract_m3u8(hls_url))
self._sort_formats(formats) self._sort_formats(formats)
return { return {
@ -87,6 +83,7 @@ class YospaceIE(InfoExtractor):
'formats': formats, 'formats': formats,
} }
class ReutersIE(YospaceIE): class ReutersIE(YospaceIE):
_VALID_URL = r'http://(?:www\.)?reuters.com/.*?(?P<id>[^/]+)$' _VALID_URL = r'http://(?:www\.)?reuters.com/.*?(?P<id>[^/]+)$'
_TESTS = [ _TESTS = [
@ -123,15 +120,17 @@ class ReutersIE(YospaceIE):
javascript_chunks = re.findall(r'<script[^>]+text/javascript[^>]*>(.*?)</script>', webpage, re.DOTALL) javascript_chunks = re.findall(r'<script[^>]+text/javascript[^>]*>(.*?)</script>', webpage, re.DOTALL)
if not javascript_chunks: if not javascript_chunks:
return return
def msub(m): def msub(m):
s = m.group(1) s = m.group(1)
if rdata.get(s): if rdata.get(s):
s = rdata.get(s) s = rdata.get(s)
return ': "' + s + '",\n' return ': "' + s + '",\n'
return ': False,\n' return ': False,\n'
vidnum = 0 vidnum = 0
for innerhtml in javascript_chunks: for innerhtml in javascript_chunks:
drawplayer_js = re.search(r'Reuters.yovideo.drawPlayer\((\{[^\}]+://.+?\})\);',innerhtml,re.DOTALL); drawplayer_js = re.search(r'Reuters.yovideo.drawPlayer\((\{[^\}]+://.+?\})\);', innerhtml, re.DOTALL)
if drawplayer_js: if drawplayer_js:
vidnum += 1 vidnum += 1
drawplayer_js = re.sub(r'".+?"\s*:\s*[^\d"\'].+?,\n', '', drawplayer_js.group(1)) drawplayer_js = re.sub(r'".+?"\s*:\s*[^\d"\'].+?,\n', '', drawplayer_js.group(1))
@ -145,12 +144,12 @@ class ReutersIE(YospaceIE):
if re.search(r'^\s*Reuters\.([^\s\[\]\.]+\.[^\[\]]+?)\s*=\s*[\'\"\d].+?;\s*\n', innerhtml, re.M): if re.search(r'^\s*Reuters\.([^\s\[\]\.]+\.[^\[\]]+?)\s*=\s*[\'\"\d].+?;\s*\n', innerhtml, re.M):
js_vars = re.findall(r'^\s*Reuters\.([^\s\[\]\.]+\.[^\s\[\]\.]+)\s*=\s*[\'"]?(.*?)[\'"]?;\s*\n', innerhtml, re.M) js_vars = re.findall(r'^\s*Reuters\.([^\s\[\]\.]+\.[^\s\[\]\.]+)\s*=\s*[\'"]?(.*?)[\'"]?;\s*\n', innerhtml, re.M)
for ent in js_vars: for ent in js_vars:
if re.search(r'["\'].+?[\(\)\+]',ent[1]):
continue
if not ent[1]: if not ent[1]:
continue continue
if re.search(r'["\'].+?[\(\)\+]', ent[1]):
continue
rdata[ent[0]] = ent[1] rdata[ent[0]] = ent[1]
drawplayer_js = re.search(r'Reuters.yovideo.drawPlayer\((\{.+?\})\);',innerhtml,re.DOTALL); drawplayer_js = re.search(r'Reuters.yovideo.drawPlayer\((\{.+?\})\);', innerhtml, re.DOTALL)
if drawplayer_js: if drawplayer_js:
vidnum += 1 vidnum += 1
ds = drawplayer_js.group(1) ds = drawplayer_js.group(1)
@ -163,7 +162,6 @@ class ReutersIE(YospaceIE):
return ret return ret
def _real_extract(self, url): def _real_extract(self, url):
from .yospace import YospaceIE
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
ret = [] ret = []
@ -186,7 +184,7 @@ class ReutersIE(YospaceIE):
if yo_id_str: if yo_id_str:
yo_id = yo_id_str.group(1) + '/' + yo_id_str.group(2) yo_id = yo_id_str.group(1) + '/' + yo_id_str.group(2)
murl = 'http://mas-e.cds1.yospace.com/mas/' + yo_id + '?trans=json' murl = 'http://mas-e.cds1.yospace.com/mas/' + yo_id + '?trans=json'
yurl = 'http://csm-e.cds1.yospace.com/csm/'+yo_id # yurl = 'http://csm-e.cds1.yospace.com/csm/'+yo_id
formats.extend(self._extract_formats(murl, video_id)) formats.extend(self._extract_formats(murl, video_id))
if formats: if formats:
self._sort_formats(formats) self._sort_formats(formats)
@ -202,5 +200,3 @@ class ReutersIE(YospaceIE):
if len(ret) > 1: if len(ret) > 1:
return self.playlist_result(ret, video_id, 'reuters') return self.playlist_result(ret, video_id, 'reuters')
return ret[0] return ret[0]