added stock scraper, converted all scripts to python 2/3 compatibility

.gitignore

@@ -1,3 +1,5 @@
 .pyc
 .DS_Store
 _tmp
+env
+__pycache__

02_find_all_links.py

@@ -1,18 +1,18 @@
-import urllib2
+import requests
 import re
 
 # get url
-url =raw_input('Enter a URL (include `http://`): ')
+url = input('Enter a URL (include `http://`): ')
 
 # connect to the url
-website = urllib2.urlopen(url)
+website = requests.get(url)
 
 # read html
-html = website.read()
+html = website.text
 
 # use re.findall to grab all the links
 links = re.findall('"((http|ftp)s?://.*?)"', html)
 
 # output links
 for link in links:
-	print link[0]
+    print(link[0])

03_simple_twitter_manager.py

@@ -16,10 +16,13 @@ twitter_api = twitter.Api(
 if __name__ == '__main__':
     follower_ids = twitter_api.GetFollowerIDs()
     following_ids = twitter_api.GetFriendIDs()
-    zombie_follows = [following_id for following_id in following_ids if following_id not in follower_ids]
+    zombie_follows = [following_id for following_id in
+                      following_ids if following_id not in follower_ids]
 
-    confirm = raw_input("Are you sure you want to unfollow %s tweeps [y|n]? " % (len(zombie_follows)))
+    confirm = raw_input(
+        "Are you sure you want to unfollow {0} tweeps [y|n]? ".format(
+            (len(zombie_follows))))
     if confirm.lower() == 'y':
         for id in zombie_follows:
             user = twitter_api.DestroyFriendship(user_id=id)
-            print "Unfollowed %s" % (user.screen_name)
+            print("Unfollowed {0}".format(user.screen_name))

04_rename_with_slice.py

@@ -8,7 +8,7 @@ for file in glob.glob("*.json"):
     new_file_name = file_name[:-6] + extension
     try:
         os.rename(file, new_file_name)
-    except OSError, e:
+    except OSError as e:
-        print e
+        print(e)
     else:
-        print "Renamed {} to {}".format(file, new_file_name)
+        print("Renamed {} to {}".format(file, new_file_name))

05_load_json_without_dupes.py

@@ -1,11 +1,9 @@
-import json
-
 def dict_raise_on_duplicates(ordered_pairs):
     """reject duplicate keys"""
     my_dict = dict()
     for key, values in ordered_pairs:
         if key in my_dict:
-           raise ValueError("Duplicate key: {}".format(key,))
+            raise ValueError("Duplicate key: {}".format(key,))
         else:
-           my_dict[key] = values
+            my_dict[key] = values
     return my_dict

06_execution_time.py

@@ -13,6 +13,7 @@ For example:
 
 
 import time
+import random
 
 
 class ExecutionTime:
@@ -25,9 +26,9 @@ class ExecutionTime:
 
 # ---- run code ---- #
 
-import random
 
 timer = ExecutionTime()
 sample_list = list()
-my_list = [random.randint(1, 888898) for num in xrange(1, 1000000) if num % 2 == 0]
+my_list = [random.randint(1, 888898) for num in
-print 'Finished in {} seconds.'.format(timer.duration())
+           range(1, 1000000) if num % 2 == 0]
+print('Finished in {} seconds.'.format(timer.duration()))

07_benchmark_permissions_loading_django.py

@@ -14,8 +14,8 @@ def timeit(method):
         te = time.time()
         all_times.append(te - ts)
 
-        print all_times
+        print(all_times)
-        print numpy.mean(all_times)
+        print(numpy.mean(all_times))
         return result
 
     return timed

08_basic_email_web_crawler.py

@@ -1,6 +1,9 @@
 import requests
 import re
-import urlparse
+try:
+    from urllib.parse import urljoin
+except ImportError:
+    from urlparse import urljoin
 
 # regex
 email_re = re.compile(r'([\w\.,]+@[\w\.,]+\.\w+)')
@@ -20,13 +23,13 @@ def crawl(url):
     # Find links
     links = link_re.findall(req.text)
 
-    print "\nFound {} links".format(len(links))
+    print("\nFound {} links".format(len(links)))
 
     # Search links for emails
     for link in links:
 
         # Get an absolute URL for a link
-        link = urlparse.urljoin(url, link)
+        link = urljoin(url, link)
 
         # Find all emails on current page
         result.update(email_re.findall(req.text))
@@ -36,7 +39,7 @@ def crawl(url):
 if __name__ == '__main__':
     emails = crawl('http://www.realpython.com')
 
-    print "\nScrapped e-mail addresses:"
+    print("\nScrapped e-mail addresses:")
     for email in emails:
-        print email
+        print(email)
-    print "\n"
+    print("\n")

09_basic_link_web_crawler.py

@@ -1,6 +1,9 @@
 import requests
 import re
-import urlparse
+try:
+    from urllib.parse import urljoin
+except ImportError:
+    from urlparse import urljoin
 
 # regex
 link_re = re.compile(r'href="(.*?)"')
@@ -17,17 +20,15 @@ def crawl(url):
     # Find links
     links = link_re.findall(req.text)
 
-    print "\nFound {} links".format(len(links))
+    print("\nFound {} links".format(len(links)))
 
     # Search links for emails
     for link in links:
 
         # Get an absolute URL for a link
-        link = urlparse.urljoin(url, link)
+        link = urljoin(url, link)
-
-        print link
 
+        print(link)
 
 if __name__ == '__main__':
     crawl('http://www.realpython.com')
-

10_find_files_recursively.py

@@ -2,7 +2,7 @@ import fnmatch
 import os
 
 # constants
-PATH = '/../../../..'
+PATH = './'
 PATTERN = '*.py'
 
 
@@ -14,17 +14,17 @@ def get_file_names(filepath, pattern):
                 # matches.append(os.path.join(root, filename))  # full path
                 matches.append(os.path.join(filename))  # just file name
         if matches:
-            print "Found {} files:".format(len(matches))
+            print("Found {} files:".format(len(matches)))
             output_files(matches)
         else:
-            print "No files found."
+            print("No files found.")
     else:
-        print "Sorry that path does not exist. Try again."
+        print("Sorry that path does not exist. Try again.")
 
 
 def output_files(list_of_files):
     for filename in list_of_files:
-        print filename
+        print(filename)
 
 
 if __name__ == '__main__':

11_optimize_images_with_wand.py

@@ -1,9 +1,9 @@
 import fnmatch
 import os
 
-# sudo pip install Wand
+# pip install Wand
 from wand.image import Image
-# sudo pip install http://pypi.python.org/packages/source/h/hurry.filesize/hurry.filesize-0.9.tar.gz
+# pip install http://pypi.python.org/packages/source/h/hurry.filesize/hurry.filesize-0.9.tar.gz
 from hurry.filesize import size
 
 
@@ -19,12 +19,13 @@ def get_image_file_names(filepath, pattern):
             for filename in fnmatch.filter(filenames, pattern):
                 matches.append(os.path.join(root, filename))  # full path
         if matches:
-            print "Found {} files, with a total file size of {}.".format(len(matches), get_total_size(matches))
+            print("Found {} files, with a total file size of {}.".format(
+                len(matches), get_total_size(matches)))
             return matches
         else:
-            print "No files found."
+            print("No files found.")
     else:
-        print "Sorry that path does not exist. Try again."
+        print("Sorry that path does not exist. Try again.")
 
 
 def get_total_size(list_of_image_names):
@@ -35,7 +36,7 @@ def get_total_size(list_of_image_names):
 
 
 def resize_images(list_of_image_names):
-    print "Optimizing ... "
+    print("Optimizing ... ")
     for index, image_name in enumerate(list_of_image_names):
         with open(image_name) as f:
             image_binary = f.read()
@@ -43,7 +44,7 @@ def resize_images(list_of_image_names):
             if img.height >= 600:
                 img.transform(resize='x600')
                 img.save(filename=image_name)
-    print "Optimization complete."
+    print("Optimization complete.")
 
 
 if __name__ == '__main__':

12_csv_split.py

@@ -117,10 +117,10 @@ def parse_file(arguments):
                 writer = writer.writerows(chunk)
 
             # Output info
-            print ""
+            print("")
-            print "Chunk # {}:".format(current_chunk)
+            print("Chunk # {}:".format(current_chunk))
-            print "Filepath: {}".format(current_output)
+            print("Filepath: {}".format(current_output))
-            print "# of rows: {}".format(len(chunk))
+            print("# of rows: {}".format(len(chunk)))
 
             # Create new chunk
             current_chunk += 1

13_random_name_generator.py

@@ -10,7 +10,7 @@ def random_name_generator(first, second, x):
          - number of random names
     """
     names = []
-    for i in xrange(0, int(x)):
+    for i in range(0, int(x)):
         random_first = randint(0, len(first)-1)
         random_last = randint(0, len(second)-1)
         names.append("{0} {1}".format(
@@ -23,4 +23,4 @@ def random_name_generator(first, second, x):
 first_names = ["Drew", "Mike", "Landon", "Jeremy", "Tyler", "Tom", "Avery"]
 last_names = ["Smith", "Jones", "Brighton", "Taylor"]
 names = random_name_generator(first_names, last_names, 5)
-print '\n'.join(names)
+print('\n'.join(names))

15_check_my_environment.py

@@ -11,7 +11,7 @@ class Main:
         pass
 
     def process(self):
-        print "ok"
+        print("ok")
 
 if __name__ == "__main__":
     m = Main(some_script.CONFIGFILE)
@@ -39,7 +39,7 @@ CONFIGFILE = get_config_file()
 if CONFIGFILE is None:
     sys.exit("Configuration error! Unknown environment set. \
               Edit config.py and set appropriate environment")
-print "Config file: {}".format(CONFIGFILE)
+print("Config file: {}".format(CONFIGFILE))
 if not os.path.exists(CONFIGFILE):
     sys.exit("Configuration error! Config file does not exist")
-print "Config ok ...."
+print("Config ok ....")

18_zipper.py

@@ -3,7 +3,7 @@ from datetime import datetime
 from zipfile import ZipFile
 
 
-#set file name and time of creation
+# set file name and time of creation
 today = datetime.now()
 file_name = 'zipper_' + today.strftime('%Y.%m.%dh%H%M') + '.zip'
 dir_name = 'tmp/'  # update path

20_restore_file_from_git.py

@@ -1,9 +1,9 @@
 from subprocess import check_output, call
 
 
-file_name = str(raw_input('Enter the file name: '))
+file_name = str(input('Enter the file name: '))
 commit = check_output(["git", "rev-list", "-n", "1", "HEAD", "--", file_name])
-print str(commit).rstrip()
+print(str(commit).rstrip())
 call(["git", "checkout", str(commit).rstrip()+"~1", file_name])
 
 

22_git_tag.py

@@ -10,5 +10,5 @@ if len(sys.argv) == 3:
     subprocess.call(command, shell=True)
     subprocess.call('git push --tags', shell=True)
 else:
-    print 'usage: tag.py TAG_NAME COMMIT'
+    print('usage: tag.py TAG_NAME COMMIT')
     sys.exit(1)

24_sql2csv.py

@@ -3,7 +3,7 @@ import csv
 import sqlite3
 
 if len(sys.argv) < 3:
-    print "Use: {0} DATABASE_NAME TABLE_NAME".format(sys.argv[0])
+    print("Use: {0} DATABASE_NAME TABLE_NAME".format(sys.argv[0]))
     exit()
 
 conn = sqlite3.connect(sys.argv[1])

25_ip2geolocation.py

@@ -9,7 +9,7 @@ def get_addresses(filename):
     row info from the csv file.
     """
     all_addresses = []
-    with open(filename, 'rb') as f:
+    with open(filename, 'rt') as f:
         reader = csv.reader(f)
         for row in reader:
             all_addresses.append(row)
@@ -29,7 +29,7 @@ def get_geolocation(all_the_ip_address):
     header_row.extend(['Country', 'City'])
     # get geolocation
     for line in all_the_ip_address:
-        print "Grabbing geo info for row # {0}".format(counter)
+        print("Grabbing geo info for row # {0}".format(counter))
         r = requests.get('https://freegeoip.net/json/{0}'.format(line[0]))
         line.extend([str(r.json()['country_name']), str(r.json()['city'])])
         updated_addresses.append(line)
@@ -43,10 +43,15 @@ def create_csv(updated_address_list):
     Given the updated lists of lists from `get_geolocation()`, this function
     creates a new CSV.
     """
-    with open('output.csv', 'wb') as f:
+    import sys
+    if sys.version_info >= (3, 0, 0):
+        f = open('output.csv', 'w', newline='')
+    else:
+        f = open('output.csv', 'wb')
+    with f:
         writer = csv.writer(f)
         writer.writerows(updated_address_list)
-    print "All done!"
+    print("All done!")
 
 
 if __name__ == '__main__':

26_stock_scraper.py

@@ -0,0 +1,32 @@
+import requests
+from lxml import html
+from collections import defaultdict
+
+
+def get_stocks(url):
+    # Make Request
+    page = requests.get(url)
+    # Parse/Scrape
+    tree = html.fromstring(page.text)
+    xpath = '//*[@id="mw-content-text"]/table[1]'
+    rows = tree.xpath(xpath)[0].findall("tr")
+    rows = [(row.getchildren()[0], row.getchildren()[3]) for row in rows[1:]]
+    rows = [(row[0].getchildren()[0].text, row[1].text) for row in rows]
+    industries = defaultdict(list)
+    for row in rows:
+        industries[row[1]].append(row[0])
+    return industries
+
+
+def output_data(data_dict):
+    for industry in data_dict:
+        print('\n'+industry)
+        print('-'*len(industry))
+        for ticker in data_dict[industry]:
+            print(ticker)
+
+
+if __name__ == '__main__':
+    url = 'http://en.wikipedia.org/wiki/List_of_S%26P_500_companies'
+    scraped_data = get_stocks(url)
+    output_data(scraped_data)

readme.md

@@ -25,3 +25,4 @@
 1. **23_flask_session_test.py**: Just a simple app to see if the sessions are working
 1. **24_sql2csv.py**: SQL to CSV.
 1. **25_ip2geolocation.py**: Given a CSV file with an ip address (see sample - *25_sample_csv.csv*), return the geolocation based on the ip.
+1. **26_stock_scraper.py**: Scrape the S&P 500 Companies list from Wikipedia, then output he data.

requirements.txt

@@ -0,0 +1,10 @@
+Flask==0.10.1
+Jinja2==2.7.3
+MarkupSafe==0.23
+Wand==0.4.0
+Werkzeug==0.10.4
+hurry.filesize==0.9
+itsdangerous==0.24
+lxml==3.4.4
+numpy==1.9.2
+requests==2.7.0