diff options
| -rw-r--r-- | lib/bb/fetch2/wget.py | 11 |
1 files changed, 8 insertions, 3 deletions
diff --git a/lib/bb/fetch2/wget.py b/lib/bb/fetch2/wget.py index d208f5ee2..368c64433 100644 --- a/lib/bb/fetch2/wget.py +++ b/lib/bb/fetch2/wget.py @@ -52,6 +52,12 @@ class WgetProgressHandler(bb.progress.LineFilterProgressHandler): class Wget(FetchMethod): + + # CDNs like CloudFlare may do a 'browser integrity test' which can fail + # with the standard wget/urllib User-Agent, so pretend to be a modern + # browser. + user_agent = "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:84.0) Gecko/20100101 Firefox/84.0" + """Class to fetch urls via 'wget'""" def supports(self, ud, d): """ @@ -303,7 +309,7 @@ class Wget(FetchMethod): # Some servers (FusionForge, as used on Alioth) require that the # optional Accept header is set. r.add_header("Accept", "*/*") - r.add_header("User-Agent", "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.2.12) Gecko/20101027 Ubuntu/9.10 (karmic) Firefox/3.6.12") + r.add_header("User-Agent", self.user_agent) def add_basic_auth(login_str, request): '''Adds Basic auth to http request, pass in login:password as string''' import base64 @@ -407,9 +413,8 @@ class Wget(FetchMethod): """ f = tempfile.NamedTemporaryFile() with tempfile.TemporaryDirectory(prefix="wget-index-") as workdir, tempfile.NamedTemporaryFile(dir=workdir, prefix="wget-listing-") as f: - agent = "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.2.12) Gecko/20101027 Ubuntu/9.10 (karmic) Firefox/3.6.12" fetchcmd = self.basecmd - fetchcmd += " -O " + f.name + " --user-agent='" + agent + "' '" + uri + "'" + fetchcmd += " -O " + f.name + " --user-agent='" + self.user_agent + "' '" + uri + "'" try: self._runwget(ud, d, fetchcmd, True, workdir=workdir) fetchresult = f.read() |