From 31e539c7261aba84da9aac171b0ec71a121d9a91 Mon Sep 17 00:00:00 2001
From: Dennis Eckerskorn <denniseckerskorn@gmail.com>
Date: Sun, 8 Dec 2024 18:29:52 +0100
Subject: [PATCH] Scrapper works but shuts down with no errors

---
 .../__pycache__/scrapper.cpython-313.pyc      | Bin 5689 -> 5948 bytes
 src/services/scrapper.py                      |  40 +++++++++++-------
 .../centered_window.cpython-313.pyc           | Bin 12811 -> 13139 bytes
 src/ui/centered_window.py                     |  14 ++++--
 4 files changed, 35 insertions(+), 19 deletions(-)

diff --git a/src/services/__pycache__/scrapper.cpython-313.pyc b/src/services/__pycache__/scrapper.cpython-313.pyc
index 035996ed0328f3789fd374a0f29cd9c779a99885..5d6b58b6352fd3965915cc1914d0737cd0e73318 100644
GIT binary patch
delta 825
zcmZ8eO-vI(6yDk0X}8<ywv?rmpVlojVzE>d8-W7>O$;LRz|zD-r7Ue}HYvN!wpGK)
zlYxYUknx9`dgEkbdLl7ixOssprA=d$gEuv5iHQeIoYF*yFPS&<-uLDGe6tmN6%r0@
zHl8B(vlLBz6xM~W!1D5U4+D7YXLop(APhN&kMSRNM3N}#CM4mJ$#fJ5)Bqg@jaZ_h
z_?Fq{Pq8OB%rTl`18~W6O;h8lf@7xExtXQbMx-TlDH}JGjH;!iq&6(&yGh9iNhYO?
zp=Wd>uIk!$LCR~26rG-w?rc9#s|h6(39yEXP^<P-G8fAm>DYpyFUIn!;U!u86h<Z_
z^2m-6cb__F?O0}4QAKc;g|4E|^-l0FGaszNd(^Zmp545%8QyiC-$NHF$Wca}Mbx<=
zmyquhL7kUMXb^Xs9)aG%mZ{2uP~o9<6VM#MBep?art6|;Y?Q^LP#l&SnH>T|4tCm1
z^8c9(Wm8=^**w66=>|x+bTc*HhF{w{+M&!vA;B#t@u?1qvf|ISb{jlaw9yaAe4}5=
z8bG*Hh<L2I<h@+%u9_gKR85+0EGp>$sKRVc$tAHW^mbRdgql_6)5%060F7ocMU~Ad
z^VzB;u4@ZwDsLq53&9Vr<0fYt{vx<dR|zM(ig~-&z0p^6omsXXaLr}TQ{+6)#&_#?
z9}d|s2KQ0;2Sc^A6LihKV&8y!oVW6iIYF3jxpPJzsTOB203u$uuK^eKIePgiH`$RQ
zS}=Hw6Y)1YhgHYrLcwtxfE#3xK`@OcoHN0F$2@7#<~=~JGV&CWXAhmKAm`fT%H(RK
zQcu=DuY|n6zSD&_P91<*JS>L5TtOAhpvO|*<TP;)s2VN8QBVtVaHuBI&{N}FaG=)D
a!~U8ZKWWJT6>~11gPR4wU8Cy$X!5__de4sl

delta 572
zcmZ9HPiqrl5XRrx-FG)lHoI@Ko5Ut*x=EvDOInl~^rEyvr3gu&X`obSur`KZZ6rz6
zqbJdeAxukypTL{Qo(g^ikw{EKK7t^W?ZtzFZ|a|e12YWs{05%q!@_Y!JM;U!gx9rR
zse0`1Xx~72|6^7J52mG0UXd%~KHI^c(oH2uNQtab+@jM|s0y}-U209{ZLtyN&`7UV
zTIK!5Zuvo@{;0fP!-$-h6I^M|<3oAM7^>_<jrY`exA;X(o{B`(@tu4K7o8PlB!TT%
z>RXUU{Na#bVIqvvrfC&{^245364xZY{8xJtZfTL2P!vm`k)pIHW`*B~MM{D}R_Ab2
ziv@)uEm5w^|8#6?(TI?Rzi=)?h>uvLs@NVJXnDM)+p)Y&8wMvvQtRG!bL4APp0&zP
zYdbtAzSh%_M@PRRFLR<<!>@WmKB{->FMVjStFgYC9jcLb;Z>o#GEh@4C820zo}>3g
z1TgV{wc$3V19K8j=EHyx$0va$mRtSfLrQWtcXfPDP3Lo98DJev<2u~IoUxwiv+W^^
zp0H$(CHrh<$ihczM?KKak5-Ra1D0|p$YkRCsn_{v)B!f}MrZ*xoZXNDv&z`<B|csd
sS1{=kxEV@Qt|rha*Au3T?q!9}xIugqehd}#MUqU~0Jz|i@jMUl3kxuXUjP6A

diff --git a/src/services/scrapper.py b/src/services/scrapper.py
index bd68158..dffc149 100644
--- a/src/services/scrapper.py
+++ b/src/services/scrapper.py
@@ -4,6 +4,8 @@ from bs4 import BeautifulSoup
 from urllib.parse import urljoin
 import mysql.connector
 
+#http://books.toscrape.com/ test scrap web
+
 class Scrapper:
     def __init__(self, ui_instance):
         self.ui_instance = ui_instance
@@ -31,9 +33,12 @@ class Scrapper:
         """Inicia el proceso de scraping"""
         self.running = True
         url = self.get_url_from_ui()
-        if url:
-            self.scrape_page(url)
-
+        if url:  
+            print(f"Iniciando scraping en: {url}")  
+            self.scrape_page(url)  
+        else:  
+            print("No se proporcionó una URL válida.")  
+            
     def stop_scraping(self):
         """Detiene el proceso de scraping"""
         self.running = False
@@ -65,11 +70,14 @@ class Scrapper:
     def update_ui(self, url, links):
         """Actualiza la pestaña 'Scrapping' con los enlaces encontrados"""
         tab = self.ui_instance.tabs["Scrapping"]
-        text_widget = tab.text_widget
+        text_widget = tab["text_widget"]
+
+        text_widget.configure(state="normal")
         text_widget.insert("end", f"Enlaces encontrados en {url}:\n")
         for link in links:
             text_widget.insert("end", f" - {link}\n")  
-            text_widget.see("end") 
+        text_widget.see("end") 
+        text_widget.configure(state="disabled")
 
     def save_links_to_db(self, url, links):
         """Guarda los enlaces en la base de datos"""
@@ -79,18 +87,18 @@ class Scrapper:
             cursor.execute("CREATE TABLE IF NOT EXISTS links (id INT AUTO_INCREMENT PRIMARY KEY, url TEXT, parent_url TEXT)")
             for link in links:
                 cursor.execute("INSERT INTO links (url, parent_url) VALUES (%s, %s)", (link, url))
-                connection.commit()
-                cursor.close()
-                connection.close()
+            connection.commit()
+            cursor.close()
+            connection.close()
         except:
             print(f"Error al gaurdar en la base de datos")
 
-    def get_url_from_ui(self):
-        """Obtiene la URL desde la interfaz de usuario"""
-        try:
-            url_entry = self.ui_instance.left_panel.url_entry
-            return url_entry.get()
-        except AttributeError:
-            print("No se pudo obtener la URL desde la interfaz")
-            return None
+    def get_url_from_ui(self):  
+        """Obtiene la URL desde la interfaz de usuario"""  
+        try:  
+            url_entry = self.ui_instance.left_panel.url_entry  
+            return url_entry.get()  
+        except AttributeError:  
+            print("No se pudo obtener la URL desde la interfaz")  
+            return None  
     
\ No newline at end of file
diff --git a/src/ui/__pycache__/centered_window.cpython-313.pyc b/src/ui/__pycache__/centered_window.cpython-313.pyc
index 09cd7f7e5e2a9b54811d412819f87bdf70545bb5..7fae506b2466a53b4214e4a0ff1628e936c006ee 100644
GIT binary patch
delta 1021
zcmaJ<TWAwO6rI`4Hc2;$smZ2kHcdCFvEAB7s%WjEA_c9*ie|c0RH&(mZLm%0cGU_N
ztDrv>O}&DmpcF*whcBWih~S4$P)HFUM3I6&eyJ#;;*T>8vEYaEac1V+JLlYccgNx{
zb~?V<?Zt?$A1}3@SK$eVmm3wp>HW=ftt-J%)_^y{Dx2aAA<aYtQcQ}P`IMjufbA7<
z!0Qot!V|ICq#(+TTiq(L5qmRM5U~=6CPZ)qYpBo49N5x$GH2Olgkt>&27Mt|=L^EL
zH>f&^Gq18$$|us)qQy9WrUGJtg=wEhipquS?5@FTSpu6+G{2v*DS?1*F>lt)v{JW;
zU@{j{zOdC?5QPa_nUyClR_j&-Y1v;)d$bU@hN1xo+Fe+J-!@rP3Kr22WhJwxnJYXf
znt4zP8~q-RNbp7eZ+2eZOXcS?d9y?ZDQY4uPx{wH&6}tNYwd5<bQH4#LeU!7WN|@{
zKTyK8dl2oTu%fk~cqNyKlxe&JE#ioe$kflK+1NNd^qb8zzLslWjgW{G)Pqz%eDsf)
zw^NB^8be>Xw<>3eCx>F)eTle=bHb1jGZHz`NDLcYdz0~=grOgz$@&&JSf0YA@TGh~
zX|A}XV^;^w=pGo>YiTrRGGg6BAP4qiJDd*G3i@Hn!h--2?DU|3T(OF4<zQQdL6*Om
zGyh#6cs_L|HA(L9_gkg{t!eR%Q-1AKrku)!9hZ71daoPzLr)fF8M9%Ug~C(L@MK$-
z?M>6=)srjkEXdZZ$@<r(O((6HXB8tDcR^e55k3Ybp)kG-O`+5H9AraooTiK$euYZ#
z4G=5u;&FIfS%q(BK3DEB3Hlf-bg=p=zL!zd=e&4?-t}t?F2m2-EBGc{tgFFiVXAHk
zew(q>Z^50nXf!9cBvM8~PsBTusrbO&`uOht{(W7s9Y%5>^@%17v7dPqy|dV}j;fcI
zYQ37?Rg3<ZZu(OOgA7~@+zgJw&4x;xg*OcyzGI9?GZ<%3&mh9!7OaW%3QL7~Uxy(R
fS&xsOXncS_z{AEyDaK<pO-^-=cYa6gJY)C=L4opO

delta 771
zcmaixNoZ416o&7~dl^XHdu`_QWqN6bHnnDGsSsSa5N$z2F*lE3vvX?Es+bn3U~!^g
zO_9nG2XGURf<o1j>c)-Wun-GEbt8hVL=glP-Nc3W)}#n7Jd2NW&i&8CT|H3Ur+k-X
zD`EC!MIW7s)fAuMm5A-Wh5$n!QRzq<4igOeJ5g4xf>Adj$YDI?^K7(IE4AfBjg;GX
zIXB%n08NjKTmE<~O9~F$WpRQV=T$e>6HZ4<rjh)4CJ?BE&(#6+s$P)-l~MJ_!Gu56
zh*O|S4%m!VGg9!N=5vc?+NNVhaf`G)CtywT8Okai^aosQD|^oHZ-v=R9c+^jMr0Q@
zBtQID?qqUpO|Au+^4|6C(bht`sdbD_#vSWfQi$=J(HRWcA^(W{eL(`>s~(BEbU`8g
z2I{6Byb(}6w0Y|w<UbQ)BN`bcNiSXwP6y7izLgP%q*&R;{b`Qv9D`U29RU|U3vED4
z_#{X;6Yj+aVJb@O85M1d;Va;<Hd$9AC%`leq@w`181>_F=K{=PIU0u=o{3)bT<7ij
z7$*29YLx_!tC)_(;TGz#hcJisco*EQ=i<jj>5X-3@lbL9)a0I{Q@EVG1NZBDdsYP7
zIbL;}<0fuSEy6wgl<I*i=t^&b)%uR~2*469WVGxDrkSuYoF;EA@=K-bwWYh#&EllF
z@|f2@<v7OS<Z$7yOcY+AmMyBYJW=JC<4AF2IF|5YcFdSD#=ebVBfAqW;85Qac!zR-
U*1cPR<UGAvx>Wi>xW6{+H;6r^C;$Ke

diff --git a/src/ui/centered_window.py b/src/ui/centered_window.py
index 7160a22..ba67152 100644
--- a/src/ui/centered_window.py
+++ b/src/ui/centered_window.py
@@ -92,11 +92,11 @@ class CenteredWindow(ctk.CTk):
 
         scrapping_label = ctk.CTkLabel(left_panel, text="Scrapping", font=("Arial", 12, "bold"))
         scrapping_label.pack(anchor=ctk.W, pady=5, padx=10)
-        url_entry = ctk.CTkEntry(left_panel, placeholder_text="Introduce la URL")
-        url_entry.pack(pady=5, padx=10)
+        url_entry = ctk.CTkEntry(left_panel, placeholder_text="Introduce la URL")  
+        url_entry.pack(pady=5, padx=10)  
 
         self.left_panel = left_panel
-        self.left_panel.url_entry = url_entry
+        self.left_panel.url_entry = url_entry  
         start_button = ctk.CTkButton(left_panel, text="Iniciar Scrapping", command=lambda:
                                      self.thread_manager.tasks["scrapper"].start(self.thread_manager.scrapper.start_scraping))
         start_button.pack(pady=5, padx=10)
@@ -118,6 +118,14 @@ class CenteredWindow(ctk.CTk):
         for tab_name in ["Scrapping", "Navegador", "Correos", "Juego", "Sistema"]:
             tab = tab_view.add(tab_name)
 
+            if tab_name == "Scrapping":
+                text_widget = ctk.CTkTextbox(tab, width=500, height=400)
+                text_widget.pack(fill=ctk.BOTH, expand=True, padx=10, pady=10)
+
+                text_widget.configure(state="disabled")
+
+                self.tabs = {"Scrapping": {"text_widget": text_widget}}
+
             if tab_name == "Sistema":
                 # Crear un frame para los gráficos del sistema  
                 system_frame = ctk.CTkFrame(tab)