Skip to content

Commit 20563e0

Browse files
mdmintzmdmintz
committed
Add presentation about web-scraping on GHA
1 parent b6d617e commit 20563e0

File tree

1 file changed

+247
-0
lines changed

1 file changed

+247
-0
lines changed

‎examples/presenter/web_scraping_on_gha.py

+247
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,247 @@
1+
from seleniumbase import BaseCase
2+
BaseCase.main(__name__, __file__)
3+
4+
5+
class UCPresentationClass(BaseCase):
6+
def test_hacking_with_cdp(self):
7+
self.open("data:,")
8+
self.set_window_position(4, 40)
9+
self._output_file_saves = False
10+
self.create_presentation(theme="serif", transition="none")
11+
self.add_slide("<h2>Press SPACE to begin!</h2>\n")
12+
self.add_slide(
13+
"<p><b><mk-0>Coming up... on the Hacker Show:</mk-0></b></p>\n"
14+
"<hr /><ul>\n"
15+
'<img src="https://seleniumbase.io/other/robot_ai.jpg"'
16+
' width="92%"></ul>\n'
17+
"<br /><br />\n"
18+
"<br /><br />\n",
19+
)
20+
self.add_slide(
21+
"<p><b>Coming up... on the Hacker Show:</b></p>\n"
22+
"<hr /><br /><ul>\n"
23+
"<li><mk-0>Unlimited free web-scraping w/ GitHub Actions&nbsp\n"
24+
"</mk-0></li>\n"
25+
"</ul>"
26+
'<img src="https://seleniumbase.io/other/gha_scraping.jpg"'
27+
' width="82%">',
28+
)
29+
self.add_slide(
30+
"<p><b>Coming up... on the Hacker Show:</b></p>\n"
31+
"<hr /><br /><ul>\n"
32+
"<li>Unlimited free web-scraping w/ GitHub Actions&nbsp"
33+
"</li><br />\n"
34+
"<li><mk-0>Using GitHub Secrets to hide within open-source"
35+
"</mk-0></li></ul>\n"
36+
'<img src="https://seleniumbase.io/other/gh_secret.png"'
37+
' width="80%">\n'
38+
"<br /><br />\n"
39+
"<br /><br />\n",
40+
)
41+
self.add_slide(
42+
"<p><b>Coming up... on the Hacker Show:</b></p>\n"
43+
"<hr /><br /><ul>\n"
44+
"<li>Unlimited free web-scraping w/ GitHub Actions&nbsp"
45+
"</li><br />\n"
46+
"<li>Using GitHub Secrets to hide within open-source"
47+
"</li><br />\n"
48+
"<li><mk-0>Launching your own, free, local proxy server"
49+
"</mk-0></li></ul>\n"
50+
'<img src="https://seleniumbase.io/other/sbase_proxy.png"'
51+
' width="80%">'
52+
"<br /><br />\n"
53+
)
54+
self.add_slide(
55+
"<p><b>Coming up... on the Hacker Show:</b></p>\n"
56+
"<hr /><br /><ul>\n"
57+
"<li>Unlimited free web-scraping w/ GitHub Actions&nbsp"
58+
"</li><br />\n"
59+
"<li>Using GitHub Secrets to hide within open-source"
60+
"</li><br />\n"
61+
"<li>Launching your own, free, local proxy server"
62+
"</li><br />\n"
63+
'<li><mk-0>Using "iptables" to make a proxy server public'
64+
"</mk-0></li></ul>\n"
65+
'<img src="https://seleniumbase.io/other/tiny_iptables.png"'
66+
' width="80%">'
67+
"<br /><br />\n",
68+
)
69+
self.add_slide(
70+
"<p><b>Coming up... on the Hacker Show:</b></p>\n"
71+
"<hr /><br /><ul>\n"
72+
"<li>Unlimited free web-scraping w/ GitHub Actions&nbsp"
73+
"</li><br />\n"
74+
"<li>Using GitHub Secrets to hide within open-source"
75+
"</li><br />\n"
76+
"<li>Launching your own, free, local proxy server"
77+
"</li><br />\n"
78+
'<li>Using "iptables" to make a proxy server public'
79+
"</li><br />\n"
80+
"<li><mk-0>And multiple live demos after the previews"
81+
"</mk-0></li><br />\n"
82+
"</ul>",
83+
)
84+
self.add_slide(
85+
"<p><b>Get ready for some serious hacking!</b></p>"
86+
'<img src="https://seleniumbase.io/other/hackers_at_comp.jpg"'
87+
' width="80%">'
88+
)
89+
self.add_slide(
90+
'<img src="https://seleniumbase.io/other/web_scraping.jpg"'
91+
' width="100%">'
92+
)
93+
self.add_slide(
94+
"<p><mk-0>And YES, that means bypassing bot-detection!</mk-0>"
95+
'<img src="https://seleniumbase.io/other/bypassable_anti_bots.jpg"'
96+
' width="90%">'
97+
)
98+
self.add_slide(
99+
"<p><b>But first, a little bit about me...</b></p>"
100+
'<img src="https://seleniumbase.io/other/mintz_present.jpg"'
101+
' width="80%">'
102+
)
103+
self.add_slide(
104+
"<p><b>About me: (Michael Mintz)</b></p>\n"
105+
"<ul>\n"
106+
"<li>I created the <b>SeleniumBase</b> framework."
107+
"</li>\n"
108+
"<li>And I lead the Automation Team at <b>iboss</b>."
109+
"</li>\n"
110+
"</ul>"
111+
'<img src="https://seleniumbase.io/other/iboss_me_2.jpg"'
112+
' width="60%">'
113+
)
114+
self.add_slide(
115+
"<p><b>Fun Fact</b></p><hr />\n"
116+
"<p>I once showed SeleniumBase to Sam Altman at MIT.<br />"
117+
"(Sam Altman cofounded OpenAI with Elon Musk.)"
118+
'<img src="https://seleniumbase.io/other/with_altman.jpg"'
119+
' width="90%">'
120+
)
121+
self.add_slide(
122+
"<p><b>Recently, SeleniumBase was trending on GitHub:"
123+
"</b></p>\n"
124+
'<img src="https://seleniumbase.io/other/trending_2025.png"'
125+
' width="100%">'
126+
)
127+
self.add_slide(
128+
"<p>The recent popularity can be attributed to <b>CDP Mode</b>,"
129+
"<br />which provides advanced stealth during automation.</p>"
130+
'<img src="https://seleniumbase.io/other/cdp_in_sb.jpg"'
131+
' width="100%">'
132+
)
133+
self.add_slide(
134+
"<p>That stealth is enough to bypass bot-detection<br />"
135+
"while web-scraping from <b>GitHub Actions</b>:</p>"
136+
'<img src="https://seleniumbase.io/other/gha_scraping.jpg"'
137+
' width="90%">'
138+
)
139+
self.add_slide(
140+
"<p><b>GitHub Actions</b> is free for public repositories:</p>"
141+
'<img src="https://seleniumbase.io/other/gha_info.png"'
142+
' width="90%">'
143+
)
144+
self.add_slide(
145+
'<img src="https://seleniumbase.io/other/gha_is_free.png"'
146+
' width="100%">'
147+
)
148+
self.add_slide(
149+
"<p>To hide sensitive information while using"
150+
"<br />GitHub Actions for open-source projects,"
151+
"<br />there's a feature called: <b>GitHub Secrets</b>.</p>"
152+
"<br />"
153+
"<p>That removes the limitation"
154+
r"<br />of being 100% open-source,"
155+
r"<br />while still being 100% free.</p>"
156+
)
157+
self.add_slide(
158+
'<img src="https://seleniumbase.io/other/using_secrets_in_gha.png"'
159+
' width="100%">'
160+
)
161+
self.add_slide(
162+
'<img '
163+
'src="https://seleniumbase.io/other/limits_for_gh_secrets.png"'
164+
' width="100%">'
165+
)
166+
self.add_slide(
167+
'<img src="https://seleniumbase.io/other/creating_gh_secrets.jpg"'
168+
' width="80%">'
169+
)
170+
self.add_slide(
171+
'<img src="https://seleniumbase.io/other/gh_secrets_in_wf.png"'
172+
' width="88%">'
173+
)
174+
self.add_slide(
175+
'<img '
176+
'src="https://seleniumbase.io/other/using_gh_secrets_in_py.png"'
177+
' width="88%">'
178+
)
179+
self.add_slide(
180+
"<h3>And that's the secret<br />to <b>GitHub Secrets!</b></h3>"
181+
)
182+
self.add_slide(
183+
"<h3>Up next:</h3>"
184+
"<br />"
185+
"<h2>Instant proxy server</h2>"
186+
"<br />"
187+
"<p>(Faster to launch than making Instant Coffee!)"
188+
)
189+
self.add_slide(
190+
'<h2><code>"sbase proxy"</code></h2>'
191+
"<br />"
192+
"<h3>(That's it!)</h3>"
193+
"<br />"
194+
'<img src="https://seleniumbase.io/other/sbase_proxy.png"'
195+
' width="100%">'
196+
)
197+
self.add_slide(
198+
'<p>More configuration options for "<b>sbase proxy</b>":</p>'
199+
'<img src="https://seleniumbase.io/other/instant_proxy.png"'
200+
' width="80%">'
201+
)
202+
self.add_slide(
203+
"<p>The proxy server code comes from <b>proxy.py</b>:</p>"
204+
'<img src="https://seleniumbase.io/other/proxy_dot_py.png"'
205+
' width="80%">'
206+
)
207+
self.add_slide(
208+
"<p><mk-0>"
209+
"Here's how to configure a proxy with <b>SeleniumBase</b>:</mk-0>"
210+
"</p><hr /><br /><ul>\n"
211+
'<li><mk-1>Proxy Mode via <code><b>pytest</b></code>:</mk-1>'
212+
'<br /><code>pytest --proxy="host:port"</code>'
213+
'<br /><code>pytest --proxy="user:pass@host:port"</code>'
214+
'</li><br />\n'
215+
'<li><mk-2>Proxy Mode via <code><b>SB()</b></code> manager:</mk-2>'
216+
'<br /><code>SB(proxy="host:port")</code>'
217+
'<br /><code>SB(proxy="user:pass@host:port")</code>'
218+
'</li>\n'
219+
)
220+
self.add_slide(
221+
"<h3>That's the secret to<br />instant proxy servers!</h3>"
222+
"<br /><p>(And how to use them with SeleniumBase)</p>"
223+
)
224+
self.add_slide(
225+
"<h3>How about opening up a"
226+
"<br />proxy server to the world?</h3><br />"
227+
)
228+
self.add_slide(
229+
"<h2>For that, there's <b>iptables</b></h2><br />"
230+
'<img src="https://seleniumbase.io/other/iptables_info.png"'
231+
' width="100%">'
232+
)
233+
self.add_slide(
234+
'<img src="https://seleniumbase.io/other/iptables_guide.png"'
235+
' width="100%">'
236+
)
237+
self.add_slide(
238+
"<h3>And that's the secret to<br />making a server public!</h3>"
239+
'<img src="https://seleniumbase.io/other/super_server.jpg"'
240+
' width="66%">'
241+
)
242+
self.add_slide(
243+
"<h3>Let's move on to<br />some live demos</h3>"
244+
'<img src="https://seleniumbase.io/other/hackers_at_comp.jpg"'
245+
' width="70%">'
246+
)
247+
self.begin_presentation(filename="uc_presentation.html")

0 commit comments

Comments
 (0)