Revision of apache_mirror.py

1 file changed, 6 insertions, 6 deletions

apache_mirror.py

			@@ -1,11 +1,11 @@
1	1		#!/usr/bin/env python2
2	2		# Usage: ./apache_mirror.py [BASE URL] [NUMBER OF COLUMNS]
3	3		# If the target site has more (or less) than three columns in the directory index, the second parameter is required.
4		-
	4	+
5	5		import sys
6	6		import urllib2
7	7		from bs4 import BeautifulSoup as Soup
8		-
	8	+
9	9		def do_iterate(curdir="", BASE="", COL="", fh=None):
10	10		print "Entering {}".format(BASE + curdir)
11	11		for tr in Soup(urllib2.urlopen(BASE + curdir).read()).findAll('tr')[1:]:
			@@ -15,14 +15,14 @@ def do_iterate(curdir="", BASE="", COL="", fh=None):
15	15		do_iterate(curdir + tr.a["href"], BASE, COL, fh)
16	16		else:
17	17		print "Adding {}".format(BASE + curdir + tr.a["href"])
18		-	fh.write("curl {0}{1} --create-dirs -o {1}\n".format(BASE, curdir+tr.a["href"]))
19		-
	18	+	fh.write("curl {0}{1} --create-dirs -o \"{2}\"\n".format(BASE, curdir+tr.a["href"], (curdir+tr.a["href"]).replace("%20", " ")))
	19	+
20	20		def main():
21	21		BASE=sys.argv[1] if len(sys.argv) > 1 else "http://repo.blha303.biz/"
22	22		COL=int(sys.argv[2]) if len(sys.argv) > 2 else 3
23	23		with open("getrepo.bat", "w") as fw:
24	24		do_iterate("", BASE, COL, fw)
25	25		return 0
26		-
	26	+
27	27		if __name__ == "__main__":
28		-	sys.exit(main())
	28	+	sys.exit(main())

1 file changed, 2 insertions, 3 deletions

apache_mirror_fix_for_windows.py

			@@ -1,10 +1,9 @@
1	1		with open("getrepo.bat") as f:
2		-	d = [a.strip().split(" ") for a in f.readlines()]
	2	+	d = [a.strip().replace("%", "%%").split(" ") for a in f.readlines()]
3	3
4	4		q = []
5	5		for a in d:
6		-	q.append(" ".join(a[:-1] + [a[-1].replace("/", "\\")]))
	6	+	q.append(" ".join(a[:a.index("-o")+1] + [x.replace("/", "\\") for x in a[a.index("-o")+1:]]))
7	7
8	8		with open("getrepo.bat", "w") as f:
9	9		f.write("\n".join(q))
10		-

1 file changed, 10 insertions

apache_mirror_fix_for_windows.py(file created)

		@@ -0,0 +1,10 @@
1	+	with open("getrepo.bat") as f:
2	+	d = [a.strip().split(" ") for a in f.readlines()]
3	+
4	+	q = []
5	+	for a in d:
6	+	q.append(" ".join(a[:-1] + [a[-1].replace("/", "\\")]))
7	+
8	+	with open("getrepo.bat", "w") as f:
9	+	f.write("\n".join(q))
10	+

1 file changed, 1 insertion, 1 deletion

apache_mirror.py

			@@ -15,7 +15,7 @@ def do_iterate(curdir="", BASE="", COL="", fh=None):
15	15		do_iterate(curdir + tr.a["href"], BASE, COL, fh)
16	16		else:
17	17		print "Adding {}".format(BASE + curdir + tr.a["href"])
18		-	fh.write("curl {0}{1} --create-dirs -o ./{1}\n".format(BASE, curdir+tr.a["href"]))
	18	+	fh.write("curl {0}{1} --create-dirs -o {1}\n".format(BASE, curdir+tr.a["href"]))
19	19
20	20		def main():
21	21		BASE=sys.argv[1] if len(sys.argv) > 1 else "http://repo.blha303.biz/"

1 file changed, 28 insertions

apache_mirror.py(file created)

		@@ -0,0 +1,28 @@
1	+	#!/usr/bin/env python2
2	+	# Usage: ./apache_mirror.py [BASE URL] [NUMBER OF COLUMNS]
3	+	# If the target site has more (or less) than three columns in the directory index, the second parameter is required.
4	+
5	+	import sys
6	+	import urllib2
7	+	from bs4 import BeautifulSoup as Soup
8	+
9	+	def do_iterate(curdir="", BASE="", COL="", fh=None):
10	+	print "Entering {}".format(BASE + curdir)
11	+	for tr in Soup(urllib2.urlopen(BASE + curdir).read()).findAll('tr')[1:]:
12	+	if tr.img["alt"] == "[PARENTDIR]":
13	+	continue
14	+	if tr.a["href"][-1] == "/":
15	+	do_iterate(curdir + tr.a["href"], BASE, COL, fh)
16	+	else:
17	+	print "Adding {}".format(BASE + curdir + tr.a["href"])
18	+	fh.write("curl {0}{1} --create-dirs -o ./{1}\n".format(BASE, curdir+tr.a["href"]))
19	+
20	+	def main():
21	+	BASE=sys.argv[1] if len(sys.argv) > 1 else "http://repo.blha303.biz/"
22	+	COL=int(sys.argv[2]) if len(sys.argv) > 2 else 3
23	+	with open("getrepo.bat", "w") as fw:
24	+	do_iterate("", BASE, COL, fw)
25	+	return 0
26	+
27	+	if __name__ == "__main__":
28	+	sys.exit(main())

Newer Older