def download(item, db, tries):
if item["href"] in db:
path = db.get(item["href"])
else:
f = common.retrieve_m(config["clearspace-root"] + item["href"], tries=tries)
doc = WikiDoc(f.read())
f.close()
path = doc.path + "/" + doc.filename
if want(path):
skip = False
if os.path.exists(path):
st = os.stat(path)
if st.st_mtime == doc.mtime:
skip = True
if not skip:
common.mkdirs(doc.path)
common.retrieve(config["clearspace-root"] + doc.filehref, path, force=True, tries=tries)
common.mkro(path)
os.utime(path, (doc.mtime, doc.mtime))
updatedbs(db, keep, item["href"], path)
def download(url, dest):
if url.startswith("data:"):
return
if fileset.tas(dest):
return
common.mkdirs(os.path.split(dest)[0])
try:
common.retrieve(url, dest)
if args["type"] == "html-single" and dest.endswith(".html"):
get_deps_html(url, dest)
if args["type"] == "html-single" and dest.endswith(".css"):
get_deps_css(url, dest)
common.mkro(dest)
except urllib.error.HTTPError as e:
if e.code == 403 or e.code == 404:
warn("WARNING: %s on %s, continuing..." % (e, url))
else:
raise
def download(url, dest, username, password):
pm = urllib2.HTTPPasswordMgrWithDefaultRealm()
pm.add_password(None, url, username, password)
opener = urllib2.build_opener(urllib2.HTTPBasicAuthHandler(pm))
common.mkdirs(os.path.split(dest)[0])
common.retrieve(url, dest, opener = opener, tries = 10, force = True)
common.mkro(dest)
def download(url, dest, username, password):
pm = urllib.request.HTTPPasswordMgrWithDefaultRealm()
pm.add_password(None, url, username, password)
opener = urllib.request.build_opener(
urllib.request.HTTPBasicAuthHandler(pm))
common.mkdirs(os.path.split(dest)[0])
common.retrieve(url, dest, opener=opener, tries=10, force=True)
common.mkro(dest)
def download_item(item, extension, tries = 1):
dstfile = os.path.join(item.type_, item.pageurl.split("/")[-1]) + extension
common.mkdirs(item.type_)
try:
print("\r[%u]" % item.number, end = "", file = sys.stderr)
common.retrieve(item.dlurl, dstfile, tries = tries)
common.mkro(dstfile)
except urllib.error.HTTPError as e:
warn("can't download item at %s (#%u, %s, %s) (%s), continuing..." % \
(item.dlurl, item.number, item.title, item.type_, e))
def download_item(item, extension, tries=1):
dstfile = os.path.join(item.type_, item.pageurl.split("/")[-1]) + extension
common.mkdirs(item.type_)
try:
print("\r[%u]" % item.number, end="", file=sys.stderr)
common.retrieve(item.dlurl, dstfile, tries=tries)
common.mkro(dstfile)
except urllib.error.HTTPError as e:
warn("can't download item at %s (#%u, %s, %s) (%s), continuing..." % \
(item.dlurl, item.number, item.title, item.type_, e))
def sync(query, keep):
xml = common.retrieve_m(config["gsa-url"] + "?client=internal&output=xml&num=1000&filter=0&q=" + query, tries = 10)
xml = lxml.etree.parse(xml)
if int(xml.xpath("//M/text()")[0]) == 1000:
raise Exception("search returned too many results")
for result in xml.xpath("//U/text()"):
dest = result.split("//")[1]
dest = dest.replace("~", "")
common.mkdirs(os.path.split(dest)[0])
common.retrieve(result, dest, tries = 10)
common.mkro(dest)
keep.add(dest)
def sync(query, keep):
xml = common.retrieve_m(
config["gsa-url"] +
"?client=internal&output=xml&num=1000&filter=0&q=" + query,
tries=10)
xml = lxml.etree.parse(xml)
if int(xml.xpath("//M/text()")[0]) == 1000:
raise Exception("search returned too many results")
for result in xml.xpath("//U/text()"):
dest = result.split("//")[1]
dest = dest.replace("~", "")
common.mkdirs(os.path.split(dest)[0])
common.retrieve(result, dest, tries=10)
common.mkro(dest)
keep.add(dest)
def save(args):
jnlpurl = args.url
if re.search("/internal/", jnlpurl):
login(args)
if re.search("/(mr|p).jnlp\?", jnlpurl):
jnlpurl = getjnlpurl(jnlpurl)
vcrfile = urllib.parse.parse_qs(jnlpurl[jnlpurl.index("?") + 1:])["psid"][0]
jnlpfile = vcrfile + ".jnlp"
common.retrieve(jnlpurl, jnlpfile, force = True)
try:
xml = lxml.etree.parse(jnlpfile).getroot()
except lxml.etree.XMLSyntaxError:
os.unlink(jnlpfile)
print("%s: couldn't retrieve jnlp: credentials incorrect?" % ap.prog)
sys.exit(1)
xmlargs = xml.xpath("//argument")
for i in range(len(xmlargs) - 1):
if xmlargs[i].text == "-play":
common.retrieve(xmlargs[i + 1].text, vcrfile)
xmlargs[i + 1].text = "file://" + config["elluminate-base"] + "/" + vcrfile
break
fetchjars(xml)
xml.set("codebase", "file://" + config["elluminate-base"] + "/" + JARS)
f = open(jnlpfile, "wb")
f.write(lxml.etree.tostring(xml, xml_declaration = True))
f.close()
print(jnlpfile)
def save(args):
jnlpurl = args.url
if re.search("/internal/", jnlpurl):
login(args)
if re.search("/(mr|p).jnlp\?", jnlpurl):
jnlpurl = getjnlpurl(jnlpurl)
vcrfile = urlparse.parse_qs(jnlpurl[jnlpurl.index("?") + 1:])["psid"][0]
jnlpfile = vcrfile + ".jnlp"
common.retrieve(jnlpurl, jnlpfile, force = True)
try:
xml = lxml.etree.parse(jnlpfile).getroot()
except lxml.etree.XMLSyntaxError:
os.unlink(jnlpfile)
print "%s: couldn't retrieve jnlp: credentials incorrect?" % ap.prog
sys.exit(1)
xmlargs = xml.xpath("//argument")
for i in range(len(xmlargs) - 1):
if xmlargs[i].text == "-play":
common.retrieve(xmlargs[i + 1].text, vcrfile)
xmlargs[i + 1].text = "file://" + config["elluminate-base"] + "/" + vcrfile
break
fetchjars(xml)
xml.set("codebase", "file://" + config["elluminate-base"] + "/" + JARS)
f = open(jnlpfile, "w")
f.write(lxml.etree.tostring(xml, xml_declaration = True))
f.close()
print jnlpfile
return elem.xpath(path, namespaces =
{ "xhtml" : "http://www.w3.org/1999/xhtml" })
if __name__ == "__main__":
warnings = 0
global config
config = common.load_config()
args = parse_args()
common.mkdirs(config["product-docs-base"])
os.chdir(config["product-docs-base"])
lock = common.Lock(".lock")
urlbase = "http://docs.redhat.com/docs/%(locale)s/" % args
common.retrieve(urlbase + "toc.html", "toc.html")
common.mkro("toc.html")
toc = lxml.etree.parse("toc.html").getroot()
for url in xpath(toc, "//xhtml:a[@class='type' and text()='%(type)s']/@href" % args):
url = url[2:] # trim leading ./
path = url[:url.index("/%(type)s/" % args)].replace("_", " ")
common.mkdirs(path)
path = path + "/" + url.split("/")[-1]
try:
common.retrieve(urlbase + url, path)
except urllib2.HTTPError, e:
if e.code == 403:
print >>sys.stderr, "WARNING: %s on %s, continuing..." % (e, urlbase + url)
warnings += 1
def fetchjars(xml):
for ref in sorted(xml.xpath("//@href")):
common.retrieve(xml.get("codebase") + "/" + ref, JARS + "/" + ref)
def download(opener, href, dest):
common.mkdirs(os.path.split(dest)[0])
common.retrieve(href, dest, opener = opener, tries = 10)
common.mkro(dest)
tries = tries)
doc = WikiDoc(f.read())
f.close()
path = doc.path + "/" + doc.filename
if want(path):
skip = False
if os.path.exists(path):
st = os.stat(path)
if st.st_mtime == doc.mtime:
skip = True
if not skip:
common.mkdirs(doc.path)
common.retrieve(config["clearspace-root"] + doc.filehref,
path, force = True, tries = tries)
common.mkro(path)
os.utime(path, (doc.mtime, doc.mtime))
updatedbs(db, keep, item["href"], path)
if len(index.items) != step:
break
for dirpath, dirnames, filenames in os.walk(".", topdown = False):
# remove local files which are no longer found in clearspace
for f in filenames:
path = os.path.relpath(dirpath, ".") + "/" + f
if not path.startswith("./.") and path not in keep:
os.unlink(path)
return bytes == "%PDF"
if __name__ == "__main__":
global config
config = common.load_config()
print >>sys.stderr, "Utility needs update since relaunch of www.redhat.com, feel free to submit patches..."
sys.exit(1)
common.mkdirs(config["references-base"])
os.chdir(config["references-base"])
lock = common.Lock(".lock")
common.retrieve("http://www.redhat.com/customersuccess/", "index.html")
common.mkro("index.html")
toc = lxml.html.soupparser.parse("index.html").getroot()
for url in toc.xpath("//a[substring-after(@href, '.') = 'pdf']/../../.."):
url = copy.deepcopy(url)
title = url.xpath("//h4//a/text()")[0].replace("/", "_")
href = url.xpath("//a[substring-after(@href, '.') = 'pdf']/@href")[0]
print >>sys.stderr, title
f = common.retrieve_tmpfile("http://www.redhat.com" + href)
if ispdf(f):
# a few links on /customersuccess are currently broken HTML files
common.sendfile_disk(f, title + ".pdf")
common.mkro(title + ".pdf")
f.close()
def fetchjars(xml):
for ref in sorted(xml.xpath("//@href")):
common.retrieve(xml.get("codebase") + "/" + ref, JARS + "/" + ref)
def download(url, dest):
if not os.path.exists(dest):
common.retrieve(url, dest)
common.mkro(dest)
return True
return False
