From dd95fc5ca86b6f639a5794dd46ebf262cfee349a Mon Sep 17 00:00:00 2001 From: gfw-report Date: Sat, 26 Mar 2022 05:18:36 +0000 Subject: [PATCH 1/3] Show which url fails to request. --- fetch_pdfs.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fetch_pdfs.py b/fetch_pdfs.py index b48f303..77b84be 100755 --- a/fetch_pdfs.py +++ b/fetch_pdfs.py @@ -36,7 +36,7 @@ def download_pdf(url, file_name): try: fetched_file = urllib.request.urlopen(url) except Exception as err: - print(err, file=sys.stderr) + print(url, err, file=sys.stderr) return with open(file_name, "wb") as fd: From d749b3b31495a18eeaf5d022c1691696435ba90d Mon Sep 17 00:00:00 2001 From: gfw-report Date: Sat, 26 Mar 2022 05:21:57 +0000 Subject: [PATCH 2/3] Use the latest Chrome user agent to bypass NDSS's HTTP 403. --- fetch_pdfs.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fetch_pdfs.py b/fetch_pdfs.py index 77b84be..aef4c20 100755 --- a/fetch_pdfs.py +++ b/fetch_pdfs.py @@ -34,7 +34,8 @@ def download_pdf(url, file_name): print("Now fetching %s" % url) try: - fetched_file = urllib.request.urlopen(url) + req = urllib.request.Request(url, headers={'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.84 Safari/537.36"}) + fetched_file = urllib.request.urlopen(req) except Exception as err: print(url, err, file=sys.stderr) return From 17e5cf32bcf5872be0da9556616e1ac4ca72edb0 Mon Sep 17 00:00:00 2001 From: gfw-report Date: Sat, 26 Mar 2022 05:34:57 +0000 Subject: [PATCH 3/3] Fix all seven broken links. The seven links were broken due to: HTTP 503, No route to host, SSL certificate mismatch, or SSL certificate expirations. --- references.bib | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/references.bib b/references.bib index cf55652..684969b 100644 --- a/references.bib +++ b/references.bib @@ -33,7 +33,7 @@ number = {4}, publisher = {National Academy of Sciences}, year = {2022}, - url = {https://www.pnas.org/content/pnas/119/4/e2102818119.full.pdf}, + url = {https://censorbib.nymity.ch/pdf/Chang2022a.pdf}, } @inproceedings{Kaptchuk2021a, @@ -530,7 +530,7 @@ booktitle = {Intelligent Human-Machine Systems and Cybernetics}, publisher = {IEEE}, year = {2017}, - url = {https://www.directory-root.com/wp-content/uploads/2018/02/Shadowsocks-Sniffing.pdf}, + url = {https://censorbib.nymity.ch/pdf/Deng2017a.pdf}, } @inproceedings{Yadav2018a, @@ -1185,7 +1185,7 @@ booktitle = {International Conference on Web and Social Media}, publisher = {AAAI}, year = {2015}, - url = {https://comp.social.gatech.edu/papers/icwsm15.algorithmically.hiruncharoenvate.pdf}, + url = {https://censorbib.nymity.ch/pdf/Hiruncharoenvate2015a.pdf}, } @inproceedings{Nisar2015a, @@ -1360,7 +1360,7 @@ booktitle = {On the Move to Meaningful Internet Systems}, publisher = {Springer}, year = {2009}, - url = {https://sps.cs.uni-saarland.de/maffei/resources/coopis.pdf}, + url = {https://censorbib.nymity.ch/pdf/Backes2009a.pdf}, } @inproceedings{Wang2014a, @@ -1760,7 +1760,7 @@ publisher = {ACM}, title = {{Cirripede}: Circumvention Infrastructure using Router Redirection with Plausible Deniability}, year = {2011}, - url = {https://hatswitch.org/~nikita/papers/cirripede-ccs11.pdf}, + url = {https://people.cs.umass.edu/~amir/papers/CCS11-Cirripede.pdf}, } @inproceedings{Houmansadr2013a, @@ -2206,7 +2206,7 @@ booktitle = {Computer and Communications Security}, publisher = {ACM}, year = {2012}, - url = {https://hatswitch.org/~nikita/papers/censorspoofer.pdf}, + url = {https://censorbib.nymity.ch/pdf/Wang2012a.pdf}, } @inproceedings{Wang2013a, @@ -2241,7 +2241,7 @@ title = {{Dust}: A Blocking-Resistant {Internet} Transport Protocol}, institution = {University of Texas at Austin}, year = {2011}, - url = {http://blanu.net/Dust.pdf}, + url = {http://censorbib.nymity.ch/pdf/Wiley2011a.pdf}, } @inproceedings{Winter2012a,