From 52cd1d38425e02e6a485ee3187e87ea39cad49e4 Mon Sep 17 00:00:00 2001
From: Akash R <akashaiprompt650@gmail.com>
Date: Fri, 11 Oct 2024 20:56:08 +0530
Subject: [PATCH] basic web scraping project

---
 .../quotes.toscrape.com/output.xlsx           | Bin 0 -> 5608 bytes
 .../quotes.toscrape.com/readme.md             |  53 +++++++++++
 .../quotes.toscrape.com/scrap.ipynb           |  86 ++++++++++++++++++
 3 files changed, 139 insertions(+)
 create mode 100644 Beginner_Projects/quotes.toscrape.com/output.xlsx
 create mode 100644 Beginner_Projects/quotes.toscrape.com/readme.md
 create mode 100644 Beginner_Projects/quotes.toscrape.com/scrap.ipynb

diff --git a/Beginner_Projects/quotes.toscrape.com/output.xlsx b/Beginner_Projects/quotes.toscrape.com/output.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..4ffa979ba236132d048769f75160dc3318f7296a
GIT binary patch
literal 5608
zcmZ`-1yoe)_Z_-p2*II6x<eWyq|<_-k#3MdI+YG-P#KVs8ANL6?oLNSx+DYyq!Ez#
zkI(hid-8w3d)K|Q?pk-Bxo5Al&v(A9r-_A41pol>0Y5`D3{`rx)zZ*UL+FbfeObF%
z>3O)hLj<0<yYu_FIBTP{iP{B;aTi-2c-6d)VT6<3la0x4MDafhujX<IJKNdDzU%7i
z+e`P3Kl&DX^(*B){uLJy;T{tCan>`rfqqyFY{kDsXf8Ca3`7QJV#Mlr=Q0rzE<`Lb
zxKvZRF~+ZA_Y9S;=v^*#pS@!VEGkvT!BjX)Pe{Jz$0ip`sVSMkgL4)8aDe(@_Sb&5
zb8DOyym}hFKT?=R1}JQzKYaiL0090w1uHiXn_oE~lC(8D1<50>`bYewFWjjW#b~-x
zo-aOM;?uJAj@712PV%~Ha+urZ_M`OZYedP2uuwF~)2wqz=!P1{6b^d@Qmu<mg-#KL
zMB$Z7-H2X)SPN-$)R`#7L++XG5PU0d#MLZ{w<Spt{1Gc8%|*hmaRsb5v>?xC)s$7u
zk0IpeeOS7OijXwy6{;q>L#!kuDv}{quz0lh#n(*E?PqVjYJaLIr(mKj&Di0sV0vkS
zg_wQOpM~<aY3%rNe$&=#D~P(LnR&Yc{>{Qh?$IfIguQF0--TFR(4l$Q_-n6;%MPC#
zoCGbG+JTsVGV|I5%1Vw406;ka07^77KF$K3_BJjyzwbi7xY;%`hD=LP1??a|`Pd!1
z5Os@%R##F&9K2>KUx#h$Fogrb@y@>1Nnyb)s$%2==_K39+Vz<-*t{D*KPs!PtxNbG
zeCM}ZkBCa$_pz7~m>F-V5tv^z5WWpm5WM*wx!X#J&@!tsasYHl1olx<bj&`F#n<$q
z8W=ZOGzJN<j(@A1nbQw*aE8&UT3ZB~@!HFOdUW5&&78S%l}Y4;df-vKO)dtdfdYG7
zROSAubJzLwyqpbcLyAE-)K!oU%pCmD?fr_5QPh`5?VYWTc6aridWJ{TLZ0^prsCAA
zALouz;|r5WOJ#vSdIcPJZoiG|pY{}W0WB`?`AAd`jKsRrV=vxs$ZpR%bZ&tw5LD(m
ze6pTAo-RqsD~NxnJNhGVVKdVnN*HgfJL=>;H~KQVyZDn2N%Nj=WJgJKci|_`O$T<4
zixMaJ#tnN#mE}!83hJs=`B7#7*xhS<a0DyejO*-KDrkzKVNSth7yMl^8hF{=g+1;t
zax-02#Um>bhZG>*Ijp4@fK;fCS!_=pF-aUpaaHMo@Za=?9;rTO>6%4e9Az~0!A1PC
z0;N7Wr3O0`V!YpO$V8=_L)KT`zE7FZR{ZGR$V;&Ilhyc1B!{asrH2%~onip$_&5o{
zCXCuSCEV1Jv18ItFEvG>R<h$fSR3Y!!GXuRs;;aPA6hGJO{A*aR({*dSHA+3s8S~p
zro4-v74gbZj~)|FAe0V^IH~L|0xnVp)->byF2qOuD0F)xYXAeQPluh5tALiEkgt$o
z=bv~8mEq&ZjkCEKU}}sE+6B>qJG@=vK54Cc#ZVarN{XRWB3y-tjN9xKA0&gc)hI7{
z5Yv~?QTg3ef!k*qNeK=WtnWS9ht@?vZ7N8*XOZ?JGJcmhr_eiu^htCKn09m(DlB0R
z4ZDoU+b`b~w*z?;<t%TCfjp{igjPTO5N2US(LL;=Gg1jWH!Ql7B4^RNHI(%1<9HG&
zFxgBT{qD!uL|_YJgoMVM?RQVX*caJm9qMiC&j)NTYJ(y^i#YSX{GmEVqp?E9{{HTU
zuqa;c8$*JoFn!0j1(Bk1`HaGZID2)Ba;ttmgyQMljd~@|{V}eFr^VX~PoB3*2J;7^
z5Ic2;vapdFan?Y)w$WJQc@<aV&YvYh(-WfnoK^-NL%ltZkSSb~l5bnLF6`y9_qNZb
zZigY?81k{+NYo6iP`F)t9^1dm-AS-+ZOle6@MzRVJcc4$k<NAF;gLq##456mvsT7<
zWdjNGl;cI6%9yWJ4iSkc)p%%rt4?jMVwcc3EE{y!VH_Zqwv$O_sP@ibxbySa)N6$m
zA^0#usTQQzjO9|FH7g~N{VJ)BaP&c<TgT}}mk(%3atgaH@Rfnf+T`%?&$YJurMWvY
z=?pzl`|nu3!y;axI+P-P{moz5rFH9xQn@%6-R4!Pv8bKc<E2`(w&2Ubdx5-<x&Pp?
zg^+PK7Ej{40IfLXb@#Ol6Z7Ta<mH(>n<`f%m-kJVTMs1L9bQq|752~Dl(ju(Ks`3z
zFKu>|t)$jLT^bhmz9k0g+#sS*vr47O(|C7q^I`KEk9y~0i56v%YKjcn#^tX)Pjw#F
zQg~I9VG7qZNPh6M5wgqMU*IDq;5Cjiq*&56-Tu6m2`%xv<#m?f-Da_W;ohf8wko}5
zerT#x5_CMbeCC=Wt)>O_?E+$WDr2&y(c|8r5nj>zo}7qFi7}MgcW)Q-xpf|W$g4A=
zrhVc%F6xiPa+1Nyye}ej%tqKKsA5Wqaad?PmUnhi9KGWv&Uiyz!X61*f2QeIif)q?
z@lcw4#CA|J%}x|Pv-D`F0o2THq1oZ*n#IR)HDfj=TS+6Ua*+Fak+C8YlId65u3U5l
z9%noiUXXO3k($Rc`%1~H1P^KpjEM;W7FssfBXv*NpwgB8d!fvk=i@W*<GDrRfU!a&
zgf$QFt|ndpQ!=hqobjQkc><MXab8(*_p}hPZwUB+7-lQ65UKnIB=R}7NHU(#P2scr
z>fM<!68mEkQTiktGojbjV!10igfg?2J0zv;oiD#^$F^Ynxqyfn)JFWk0su}30RY<H
z3y8OyhZDr!#>NvO@Yl~@t4O^5jK_=^`9&Io4SUe=`qz_W@OT`wK7O=Mv}*MD=B<od
zj^uiw2=GN98FOZ}H2W$CMJuL+9qPN~TKvHenDvdb8euULQjMgc_j?l7YzEwMvk`py
zgljx(v}Z>W&N78EE(L==Vy~euc@WzcLb{NJ3(N10Leu-+y08-NRc`}l6Nuz1QbrEf
zqxw`)A+teo$02XtVCPbdj;H=QB|Oy%(wf<^18p8>8;<o0$y%3Vvtf2uR8vLJhJ+WH
z=N^L5Ig{?}d&J?W^t%;8dz|v8YhT9NMvI@W9bEM+2kVdmn$rl+r(U;s@~^Hg2FOd&
z6o`3jz7aT=|F%M~q^mJz`Q21WuH1C6;v~gYck4-s%i-rNpCZRuj@Sh!4jCq*kk06*
z$EDi^!87IQBc~ZZyKC#4g2(6YZb~d&G#pGhd+g<|tZSyE5RM6^IS!;MczuCZCX&MK
zmrc7_5_x(*XT!&i&1R0GT*HKIiYbkr7<||QHGoLmtG0Rs{p&d9q?>%=Av9wM!!nxs
zaWQ<S8Ks}Kh`?FhpX@@ht>q&QiF6}0s~4{LIU1a)63FOa_vn-9Ej3@p2QZn(A0d_H
z4h=>Qxyq1r)^VJ#o9h!m7N}s$_a{d%o1-r|uUc{8E4<8_%lY>k<d=Gxne1tRbf&ve
zK^4%-u3Mc(8Q8!9PJN2T5i=WHTOpa!)=Pwt+tiL(+0LE<&0$Tf|499p6?ZMSNj$qq
zA%0+&Q?;euYR*mi9FO(cRMIxaTW-^|`ml%@Q4PG}tO21W8xeQ`DOYtBwcTVP^(+WJ
zzuuVOMAM8UG&5gP`@ZZuy)Pq6-boF<LB>WVRRsQw>6q5<qGg~JT3Z53jPDDe(!R&c
zj)@5$<Cb_x^de=V?xW-Kw^FigJ58Q7vK1GaLAQRVii*P_!=2j5J;Q;Mt&sAd3~bF4
z5re03P5F+Y6YQ~f2v6Y;8ZUzb3$^Cxa!d_cWaUxDpf$G-asri{58Jwy8w8|#$5MOL
z<C?-1?loItcpsL1Q!KBn3%+vo3J6eWS#Q*ZCh!#|;DNW967qFnm0#$0I)Ln#FC`z<
zf`lZph&fXFl<sS+ex71gPw-`mE{P3JCCwt@Q}xVpg8P%jZmeu5XCEGbF?ESSYSxE=
z#4Jz3T`dBWpsrSXx&E<`WgcK>0~j|2UPbM4{5s;ngLX<1&!fOusbP~`PQ(1bO_SC%
zm9t6NP4Rlah;-8uuWdR8M>@Uk)1)oI`*AA~)>a9lL`|Co(ij$sX9Jt3!a?JLT`$Sg
z?WsaSh@j#(vtS`-fss{AQ8RE``_+3UX+fHvd0V*{<3y2S-=307H&#!Xp5y)5EPfm(
z5WL3(09=Rw0FvL$0^;fGYy<f<XU^%*yv!6Nzo72KOV!r9pRWiP8_`Icc0|lYHoviW
z&Ssu3RA}AOEK*IGyhS>9T$U5INB_1?+FG_YcO`*gjbD=ULnQY$bn~vwROx1|We46U
zghb7$$dWYO>n%ysYSGO^xOH`71CMZ5n2xxUY=Qr3gteW@cEKUPcKJ~K9lr;Bqd6f>
zT6-(6`?%+Xxg2@gZS%rpa4$xjyi`D$5>XKb8|{S=8KqBv8MKa-h%m8nr;0`PfQclu
zQhET=VW|^)p_UcjUqfcU`Gc{OCz`w8oqKMvG&kAwbnRRDwe6C*Kct&+_h04A7jx<}
zjwI$e&Z2>C?A@nZi&OjnbaoRZN`l%OcrNsEKVuNJEPqz0+)-1%zN#PSMTw*Kqz4hu
z>2h}l!bsG+{D~cQU{1H-$-AW<wvtOb*oh-mD@qe*K52THIcFwA_roSEuG0Jp6u(TC
zUbD0~5$Q!3BHY3}_#*qLNhT=W5=l)q)iSeeJEYSH7twDF5r_6Ma7x5&iPY$9>0xOT
z;z(7NX{=$MdYFE`EYjYUf4o5^lfQp!*pF(2fWaWk9#mpp1K5(*@6c^a!<ziOn;t(R
zo7KjhwX)L)%;iQkFqYnUI&nL=<Gu;ir~|H@qWF1hri;mR;C2@_wmThCuvh$3Qwx5S
zHBMp(`R%}@Cy7O^tbrE^zQyZ}m})Aueso5|MbtxtjpDH47Iky%!mwDiI^Kgu&fb03
z8n?(YHYYIE2@7#D@K)qu`21z{z6h3}h*<C|lJbEHE2TUck$2YpB5A5o`79p&$+UnG
z8js$*M9Odl@@DrjeEn>zw|)41R&rQrYy@8tDMpQ{9>EA3ql1znIZ*@2=nrb|g;2C(
zNn<5Fv0%QPy7ooc??7%qXQ$5j>_yWl$)6Qnqq-T>imv1v=&D8+HNf1%#u*~O|LdNW
ztm%p=L@bY_urb&A(1|HjG+C+?MN}KTmixLh$*S}4IDWE~*&e8Qm7UFpBooc?qKC{N
zoVx`(O{Vnk6a&hgxGb`tz5{dL(Uj+di6(wJnk47_dcfAp*Wo%|qXjuvKO{`rtcO(E
zcoR|`VVsn7ykXT)GMaiCBBFUUG>ak}dy|DM+B$!KXE$%~;D|Z#ovN}s?_m;LE7mI&
zDVIIh3_n0vSyuWitX~~`%BPY&ZOIZuM2}1;6R^9Lp5pwO=<zd*0zvflnG2mL*>CCo
zTIVg@+?;-iH$HJ#r$dlfIT+E8_sR9Sy4I%Is}Oa3awUJ1k#|*kXWFuBDUw5-OKT~d
zqi15gugMG=MJD}D>G(<f0fhfC&&bfhtN|Z*8<~$qV@p!@nZjs(ZA=v07E>_)JSD)0
zssh?(ui(+#^|3JYm??dS)^pn!P-ZJ{7_Y-elUrf%aev??cEQQRN4e$75~mB{leVgd
zwMsAc4GRv%a)e_^`LbdBk72?KBO6JysFiz}+FjOKAJ{uAh<L#lN#es_8|F{pQS(h*
zgNQfO7?aHY>U7b_7k#W@tFX=R@5A`J8bmUJM-26W?P0X1$}c@*%4~IvIUm1cCxex2
zwk2SHQkKfLqTQ{(RCx&nfjsr@;w2`$NGu@ah-XX6n-EW#S!@>n%5N|5J=*ia%DM5|
zKGC1#ifk^|7o$o2i6$8Io7~@p^lys)Dypg^S<)AR#NkMaRRC@N7z{IyzlfS9>iH=!
z^j=wE`!-!0K#ieZ&=8g0^26FrKs3f*`u>D8#eqG0zfI2;BLFT<Ppv%ug^E4?D0hiD
zkVt1kp$gxDexZ%&W_j;Rt^0hWS1i+c8+YW2gAye6$OHq5nDUjZxwu!2S4`TSkHy-I
zk~tF*oSP<R<vQ??0Scf1u0uk_MoO?B;%=nr?6yJO9h7QqG0WoN=F+t!Gb0qk=+FsH
zpr^%OR)evUo2#ddtEc%RUw0db>8~m(PC@;uqHc4<w`Yzb67KSw{Bb;6twdp+rnz6=
zTDp0<CCrp-<dl)5Y36nx|A3sc71mf`4@%j|>ia5DF@?*24oLw=;AgWwQ`4ci%FBv+
zQ00NQ6jT>L&h3M#i*p1z^{Was`p##AVsOhPXzr&34_3SvDzkfB7dH%Ii(Xz@JR;NB
zQ|7Gm=xyu1XX37y9bFN{a>(=L(TQJ3YFvaf4`q{DkHfnP%nf^tfdP<RJ@GRas`Z@X
zmzo-J1n_R$5GbGOa2K`cUgDGU`5{+}#5%Q=F&9GMR26pcT9)%hVQjBrVy}thN|^Qb
z6i3+nQ<5`%3EdM`xYsUrSLq<rf%jXE3uBNk8SG-me;kQO>DDEQ`XY<Gi=MhMFsT6l
z+m%BT`qvSHX88Ymbl1_>4YA)?03ZaT<KO7N?Xm0d>#os1@HzC~|A&WkJ;3!{!`}g_
zLmBb^3h<wMi0e_Vj}w1K3Bk}L{wvBq!^L&z^}hWNlmXq{{?)~=1F!eNe}K4Xa}=HW
zza@Jed|l`NfUVHBBpUobRDV6rbt(N5M~&h?g{7y7gEsj900Q(Whwk91zXS;QKQ=@B
Ay8r+H

literal 0
HcmV?d00001

diff --git a/Beginner_Projects/quotes.toscrape.com/readme.md b/Beginner_Projects/quotes.toscrape.com/readme.md
new file mode 100644
index 0000000000..c08cb955db
--- /dev/null
+++ b/Beginner_Projects/quotes.toscrape.com/readme.md
@@ -0,0 +1,53 @@
+A simple web scraping program using Python that retrieves data from a website. For this example, we will scrape quotes from [quotes.toscrape.com](http://quotes.toscrape.com/), which is a site specifically designed for practicing web scraping.
+
+### Simple Web Scraping Program
+
+#### Requirements
+You'll need to install the `requests` and `BeautifulSoup` libraries. You can do this using pip:
+
+```bash
+pip install requests beautifulsoup4
+```
+
+### Explanation
+1. **Import Libraries**: The program imports the `requests` library to handle HTTP requests and `BeautifulSoup` from `bs4` to parse HTML content.
+  
+2. **Function Definition**: The `scrape_quotes()` function:
+   - Defines the URL of the site to scrape.
+   - Sends a GET request to fetch the webpage content.
+   - Checks if the response status code is 200 (OK).
+   - Parses the HTML content using BeautifulSoup.
+   - Finds all quote elements by searching for `div` tags with the class `quote`.
+   - Loops through each quote element, extracting the text and the author, and prints them.
+
+3. **Run the Scraper**: The last line calls the `scrape_quotes()` function to execute the scraping process.
+
+### How to Run the Program
+1. Ensure you have Python installed on your machine.
+2. Install the required libraries as mentioned above.
+3. Copy the provided code into a Python file (e.g., `scrape_quotes.py`).
+4. Run the script from your terminal or command prompt:
+
+   ```bash
+   python scrape_quotes.py
+   ```
+
+### Output
+The program will print out the quotes and their authors from the specified webpage, like this:
+
+```
+Quote: "The world as we have created it is a process of our thinking. It cannot be changed without changing our thinking."
+Author: Albert Einstein
+
+Quote: "It is our choices, Harry, that show what we truly are, far more than our abilities."
+Author: J.K. Rowling
+
+...
+```
+
+### Note
+- The example above is designed for educational purposes and uses a public website that allows scraping.
+- Always check a website's `robots.txt` file and terms of service to ensure that scraping is allowed.
+
+If you have any questions or need further help with web scraping, feel free to ask!
+Here's a simple script that scrapes quotes and their authors from the website:
\ No newline at end of file
diff --git a/Beginner_Projects/quotes.toscrape.com/scrap.ipynb b/Beginner_Projects/quotes.toscrape.com/scrap.ipynb
new file mode 100644
index 0000000000..ee3b2b777b
--- /dev/null
+++ b/Beginner_Projects/quotes.toscrape.com/scrap.ipynb
@@ -0,0 +1,86 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Quotes have been written to quotes.xlsx\n"
+     ]
+    }
+   ],
+   "source": [
+    "import requests\n",
+    "from bs4 import BeautifulSoup\n",
+    "import pandas as pd\n",
+    "\n",
+    "def scrape_quotes():\n",
+    "    # URL of the site to scrape\n",
+    "    url = 'http://quotes.toscrape.com/'\n",
+    "    \n",
+    "    # Send a GET request to fetch the webpage content\n",
+    "    response = requests.get(url)\n",
+    "\n",
+    "    # Check if the request was successful\n",
+    "    if response.status_code == 200:\n",
+    "        # Parse the webpage content\n",
+    "        soup = BeautifulSoup(response.text, 'html.parser')\n",
+    "\n",
+    "        # Find all quote elements\n",
+    "        quotes = soup.find_all('div', class_='quote')\n",
+    "\n",
+    "        # Lists to hold quotes and authors\n",
+    "        quotes_list = []\n",
+    "        authors_list = []\n",
+    "\n",
+    "        # Loop through the quotes and store the text and author\n",
+    "        for quote in quotes:\n",
+    "            text = quote.find('span', class_='text').text\n",
+    "            author = quote.find('small', class_='author').text\n",
+    "            quotes_list.append(text)\n",
+    "            authors_list.append(author)\n",
+    "\n",
+    "        # Create a DataFrame\n",
+    "        quotes_df = pd.DataFrame({\n",
+    "            'Quote': quotes_list,\n",
+    "            'Author': authors_list\n",
+    "        })\n",
+    "\n",
+    "        # Write the DataFrame to an Excel file\n",
+    "        quotes_df.to_excel('quotes.xlsx', index=False)\n",
+    "        print(\"Quotes have been written to quotes.xlsx\")\n",
+    "\n",
+    "    else:\n",
+    "        print(f'Failed to retrieve webpage. Status code: {response.status_code}')\n",
+    "\n",
+    "# Run the scraper\n",
+    "scrape_quotes()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}