95
96
97
98
99
100
101
102
103
104
105
106
107
108
109 | 95
96
97
98
99
100
101
102
103
104
105
106
107
108
109 |
-
+
| )
# Playlist format content probing (assert type)
playlist_content_map = [
("pls", r""" (?i)\[playlist\].*NumberOfEntries """),
("xspf", r""" <\?xml .* <playlist .* ((?i)http://xspf\.org)/ns/0/ """),
("m3u", r""" ^ \s* \#(EXT)?M3U """),
("asx" , r""" <asx\b """),
("asx" , r""" (?i) <asx\b """),
("smil", r""" <smil[^>]*> .* <seq> """),
("html", r""" (?i)<(audio|video)\b[^>]+\bsrc\s*=\s*["']?https?:// """),
("wpl", r""" <\?wpl \s+ version="1\.0" \s* \?> """),
("b4s", r""" <WinampXML> """), # http://gonze.com/playlists/playlist-format-survey.html
("jspf", r""" ^ \s* \{ \s* "playlist": \s* \{ """),
("asf", r""" ^ \[Reference\] .*? ^Ref\d+= """),
("url", r""" ^ \[InternetShortcut\] .*? ^URL= """), |
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376 | 362
363
364
365
366
367
368
369
370
371
372
373
374
375
376 |
-
+
| # regex scheme
rules = self.extr_urls[fmt]
rows = []
fields = [name for name in ("url", "title", "homepage", "genre", "playing") if rules.get(name)]
# Block-wise processing
if rules.get("split"):
for part_src in re.split(rules["split"], self.src, re.X):
for part_src in re.split(rules["split"], self.src, 0, re.X):
row = {}
for name in fields:
val = self.field(name, rules, part_src)
if val and val[0]:
row[name] = val[0]
if row.get("url"):
rows.append(row) |
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451 | 435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451 |
-
-
-
+
+
+
| url = r"(?x) <location> (\w+://[^<>\s]+) </location> ",
title = r"(?x) <title> ([^<>]+) ",
homepage = r"(?x) <info> ([^<>]+) ",
playing = r"(?x) <annotation> ([^<>]+) ",
unesc = "xml",
),
"asx": dict(
split = r" (?x) <entry[^>]*> ",
url = r" (?x) <ref \b[^>]+\b href \s*=\s* [\'\"] (\w+://[^\s\"\']+) [\'\"] ",
title = r"(?x) <title> ([^<>]+) ",
split = r" (?ix) <entry[^>]*> ",
url = r" (?ix) <ref \b[^>]+\b href \s*=\s* [\'\"] (\w+://[^\s\"\']+) [\'\"] ",
title = r" (?ix) <title> ([^<>]+) ",
unesc = "xml",
),
"smil": dict(
url = r" (?x) <(?:audio|video|media)\b [^>]+ \b src \s*=\s* [^\"\']? \s* (\w+://[^\"\'\s\>]+) ",
unesc = "xml",
),
"jspf": dict( |