new examples

Author: furas

__scraping__/myntra.com - scrapy/main.py renamed to __scraping__/myntra.com - scrapy/2017.12.23/main.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python3
+
+# date: 2019.08.14
+# https://stackoverflow.com/questions/57490072/how-to-crawl-a-website-to-get-all-the-links-in-a-website-using-scrapy-in-python/57490431#57490072
+
+import scrapy
+
+class MySpider(scrapy.Spider):
+    
+    name = "MySpider"
+
+    def __init__(self, allowed_domains=None, start_urls=None):
+        super().__init__()
+
+        # self.name = name
+        if allowed_domains is None:
+            self.allowed_domains = []
+        else:
+            self.allowed_domains = allowed_domains
+
+        if start_urls is None:
+            self.start_urls = []
+        else:
+            self.start_urls = start_urls  
+
+    def parse(self, response):
+        print('[parse] url:', response.url)
+
+        # extract all links from page
+        all_links = response.xpath('*//a/@href').extract()
+        
+        # iterate over links
+        for link in all_links:
+            print('[+] link:', link)
+            #yield scrapy.http.Request(url="http://www.myntra.com" + link, callback=self.print_this_link)
+            full_link = response.urljoin(link)
+            yield scrapy.http.Request(url=full_link, callback=self.print_this_link)
+            
+            
+    def print_this_link(self, response):
+        print('[print_this_link] url:', response.url)
+        title = response.xpath('//title/text()').get() # get() will replace extract() in the future
+        body = response.xpath('//body//text()').getall()
+        yield {'url': response.url, 'title': title, 'body': body}
+            
+        
+# --- run without creating project and save in `output.csv` ---
+
+from scrapy.crawler import CrawlerProcess
+
+c = CrawlerProcess({
+    'USER_AGENT': 'Mozilla/5.0',
+
+    # save in file as CSV, JSON or XML
+    'FEED_FORMAT': 'csv',     # csv, json, xml
+    'FEED_URI': 'output.csv', # 
+})
+c.crawl(MySpider)
+c.crawl(MySpider, allowed_domains=["myntra.com"], start_urls=["http://www.myntra.com/"])
+c.start()
+

__scraping__/myntra.com - scrapy/2019.08.14/main.py

@@ -0,0 +1,62 @@
+import random
+
+class Player():
+
+    def __init__(self, name):
+        self.name = name
+        self.score = 0
+
+    def run(self):
+        self.score += random.randint(0, 6)
+
+    def __str__(self):
+        return "{} (score: {})".format(self.name, self.score)
+
+class Team():
+    
+    def __init__(self, players):
+        self.players = players
+        self.current_batsman = 0
+        self.current_run = 0
+        
+    def set_next_batsman(self):
+        self.current_batsman += 1
+        if self.current_batsman >= len(self.players):
+            self.current_batsman = 0
+            
+    def get_current_batsman(self):
+        return self.players[self.current_batsman]
+    
+    def run(self):
+        self.players[self.current_batsman].run()
+                
+        if self.current_run % 2 != 0:
+            self.set_next_batsman()
+
+        self.current_run += 1
+        
+    def __str__(self):
+        return "Player: " + ", ".join(str(p) for p in self.players)
+        
+    def total_score(self):
+        return sum(p.score for p in self.players)
+    
+team1 = Team( [Player("a"), Player("b"), Player("c")] )
+team2 = Team( [Player("x"), Player("y"), Player("z")] )
+
+print('Team1:', team1)
+print('Team2:', team2)
+
+for number in range(1, 5):
+    print('Round:', number)
+    print('Team1 current batsman:', team1.get_current_batsman())
+    team1.run()
+    print('Team2 current batsman:', team2.get_current_batsman())
+    team2.run()
+
+print('Team1:', team1)
+print('Team2:', team2)
+
+print('Team1 total score:', team1.total_score())
+print('Team2 total score:', team2.total_score())
+

class/cricket-player-team/main.py

@@ -0,0 +1,8 @@
+import re
+
+data = ['2d1h39m53s', '1h39m53s', '39m53s', '53s']
+
+for item in data:
+    rs = re.search('(?:(\d+)d)?(?:(\d+)h)?(?:(\d+)m)?(?:(\d+)s)?', item)
+    print(rs.groups())
+    

datetime/parse-datetime-with-different-elements/main.py

@@ -0,0 +1,35 @@
+
+#------------------------------------------------------------------------------
+# decode from base64 to png
+#------------------------------------------------------------------------------
+
+import base64
+
+html = '<img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAAAAACoWZBhAAAAMklEQVR4nEXNwQkAMBACwfFI/y2bxwXia8FFUwF1pCCNJTIIwaD04ctsKRyaldI/9i8u1iwOE6FA880AAAAASUVORK5CYII=">'
+
+data_base64 = html.split('base64,')[1] # remove text before encoded data
+data_base64 = data_base64[:-2]         # remove text after encoded data
+
+#data_base64 = 'iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAAAAACoWZBhAAAAMklEQVR4nEXNwQkAMBACwfFI/y2bxwXia8FFUwF1pCCNJTIIwaD04ctsKRyaldI/9i8u1iwOE6FA880AAAAASUVORK5CYII='
+
+data_base64 = data_base64.encode()   # convert string to bytes
+data = base64.b64decode(data_base64) # decode from base64 (bytes)
+open('image.png', 'wb').write(data)  # write bytes to file
+
+
+
+#------------------------------------------------------------------------------
+# encode png to base64 and embed in html
+#------------------------------------------------------------------------------
+
+import base64
+
+data = open('image.png', 'rb').read() # read bytes from file
+data_base64 = base64.b64encode(data)  # encode to base64 (bytes)
+data_base64 = data_base64.decode()    # convert bytes to string
+
+print(data_base64)
+
+html = '<img src="data:image/png;base64,' + data_base64 + '">' # embed in html
+open('output-png.html', 'w').write(html)
+

decode-encode/base64-tiff-html/main-png.py

@@ -0,0 +1,37 @@
+
+#------------------------------------------------------------------------------
+# decode from base64 to tiff
+#------------------------------------------------------------------------------
+
+import base64
+
+html = '<img src="data:image/tiff;base64,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">'
+
+data_base64 = html.split('base64,')[1] # remove text before encoded data
+data_base64 = data_base64[:-2]         # remove text after encoded data
+
+#data_base64 = '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'
+
+data_base64 = data_base64.encode()   # convert string to bytes
+data = base64.b64decode(data_base64) # decode from base64 (bytes)
+open('image.tiff', 'wb').write(data) # write bytes to file
+
+
+
+#------------------------------------------------------------------------------
+# encode tiff to base64 and embed in html
+#------------------------------------------------------------------------------
+
+import base64
+
+data = open('image.tiff', 'rb').read() # read bytes from file
+data_base64 = base64.b64encode(data)   # encode to base64 (bytes)
+data_base64 = data_base64.decode()     # convert bytes to string
+
+print(data_base64)
+
+html = '<img src="data:image/tiff;base64,' + data_base64 + '">' # embed in html
+open('output-tiff.html', 'w').write(html)
+
+# browsers don't display tiff so html can show broken image.
+# you have to save from page to file and then you can see tiff.

decode-encode/base64-tiff-html/main-tiff.py

@@ -0,0 +1,36 @@
+from flask import Flask, request, redirect, make_response, render_template_string
+
+
+app = Flask(__name__)
+
+
+@app.route("/")
+def index():
+    args_filename = request.args.get('filename', '')
+    
+    return render_template_string('''
+Previous filename: {{ filename }}
+<hr>
+<form action="getfile" method="POST" enctype="multipart/form-data">
+    Project file path: <input type="file" name="config_file"><br>
+    <input type="submit" value="Submit">
+</form>
+''', filename=args_filename)
+
+
+@app.route('/getfile', methods=['GET','POST'])
+def getfile():
+    #print('args:', request.args)
+    #print('form:', request.form)
+    #print('files:', request.files)
+
+    result = request.files.get('config_file')
+    
+    if result:
+        result.save(result.filename) # TODO: save with unique name which couldn't overwrite file with passwords 
+        return redirect('/?filename={}'.format(result.filename))
+
+    return redirect('/')
+
+    
+app.run()    

decode-encode/base64-tiff-html/image.png renamed to decode-encode/base64-tiff-png-html/image.png

@@ -0,0 +1,39 @@
+from flask import Flask, request, redirect, make_response, render_template_string
+
+
+app = Flask(__name__)
+
+
+@app.route("/")
+def index():
+
+    cookies_filename = request.cookies.get('filename', '')
+    
+    return render_template_string('''
+Previous filename: {{ filename }}
+<hr>
+<form action="getfile" method="POST" enctype="multipart/form-data">
+    Project file path: <input type="file" name="config_file"><br>
+    <input type="submit" value="Submit">
+</form>
+''', filename=cookies_filename)
+
+
+@app.route('/getfile', methods=['GET','POST'])
+def getfile():
+    #print('args:', request.args)
+    #print('form:', request.form)
+    #print('files:', request.files)
+
+    response = make_response(redirect('/'))
+    
+    result = request.files.get('config_file')
+    
+    if result:
+        result.save(result.filename) # TODO: save with unique name which couldn't overwrite file with passwords 
+        response.set_cookie('filename', result.filename)
+
+    return response
+
+    
+app.run()    

decode-encode/base64-tiff-html/image.tiff renamed to decode-encode/base64-tiff-png-html/image.tiff

@@ -0,0 +1,39 @@
+
+```
+from flask import Flask
+
+def create_app():
+    app = Flask(__name__)
+       
+    @app.route('/')
+    def index():
+        return "Hello World!"
+
+    return app
+    
+if __name__ == '__main__':
+    app = create_app()
+    app.run()
+```
+
+If code is in file `main.py` then you can run it as
+
+    waitress-serve --call "main:create_app"
+
+If you forget `:` then you can see `"Malformed application"` 
+
+---
+
+You can still run it as 
+
+    python main.py 
+    
+----
+
+[Waitress 1.3.0](https://docs.pylonsproject.org/projects/waitress/en/stable/runner.html)
+
+---
+    
+https://stackoverflow.com/questions/25254022/flask-are-blueprints-necessary-for-app-factories 
+
+https://flask.palletsprojects.com/en/1.1.x/patterns/appfactories/

decode-encode/base64-tiff-png-html/main-png.py

@@ -0,0 +1,14 @@
+from flask import Flask
+
+def create_app():
+    app = Flask(__name__)
+       
+    @app.route('/')
+    def index():
+        return "HELLO WORLD"
+
+    return app
+    
+if __name__ == '__main__':
+    app = create_app()
+    app.run()