def xml2(self):
input = '''
<stuff>
<users>
<user x="2">
<id>001</id>
<name>Chuck</name>
</user>
<user x="7">
<id>009</id>
<name>Brent</name>
</user>
</users>
</stuff>'''
exu = ExerciseUtils()
stuff = exu.InternetTreeXML(input)
stuff.create_tree()
lst = stuff.findall_users()
print('User count:', len(lst))
field_list = [("Name:", "name", "text", ""), ("Id:", "id", "text", ""),
("Attribute:", "", "attr", "x")]
for tree in lst:
stuff.replace_tree(tree)
stuff.print_element_tree(field_list)
def urlwords(self):
print("urlwords - compute the frequency of each word in the file")
exu = ExerciseUtils()
fh = exu.open_url(exu.url_text_doc, None)
page = exu.get_url_page(fh)
count = exu.getwords(page)
assert len(count) == 26
print(count)
def curl1(self):
print("curl1 - get and image and write it to a file")
exu = ExerciseUtils()
img = exu.open_url_small_img(self.url_jpg, None)
imglen = len(img)
assert imglen == 230210
print("Length of " + self.url_jpg + " is:", imglen)
rc = exu.write_file(self.url_jpg, "wb", img)
assert rc is None
def urllib1(self):
print("urllib1 - use urllib to read a web page like a file")
exu = ExerciseUtils()
fh = exu.open_url(exu.url_text_doc, None)
assert fh != ""
page = exu.get_url_page(fh)
assert len(page) > 0
print(page)
def curl2(self):
print("curl2 - get and image and write it to a file using a buffer to\
read any size file")
exu = ExerciseUtils()
img = exu.open_url(self.url_jpg, None)
assert img != ""
count = exu.get_url_large_img_and_save(img, self.url_jpg)
assert count == 230210
print(count, 'characters copied.')
def socket1(self):
print("socket1 - World's simplest web browser")
exu = ExerciseUtils()
mysock, url = exu.init_socket_and_url(exu.url_prefix, exu.url_base,
exu.url_text_doc)
assert mysock is not None
page = exu.get_page(mysock, url)
assert len(page) == 2
mysock = exu.close_socket(mysock) # normal socket
def xml1(self):
data = '''
<person>
<name>James</name>
<phone type="intl">
+1 503 851 8418
</phone>
<email hide="yes" />
</person>'''
exu = ExerciseUtils()
inter_tree = exu.InternetTreeXML(data)
inter_tree.create_tree()
inter_tree.print_element_tree([("Name:", "name", "text", "")])
inter_tree.print_element_tree([("Attr:", "email", "attr", "hide")])
inter_tree.print_element_tree([("Name:", "name", "text", ""),
("Attr:", "email", "attr", "hide")])
def geojson(self):
data = '''
[
{ "id" : "001",
"x" : "2",
"name" : "Chuck"
} ,
{ "id" : "009",
"x" : "7",
"name" : "Brent"
}
]'''
exu = ExerciseUtils()
intr_tree = exu.InternetTreeJSON(data)
intr_tree.create_tree_list()
print('User count:', intr_tree.tree_list_count())
field_list = [("Name:", "name", "text", ""), ("Id:", "id", "text", ""),
("Attribute:", "", "attr", "x")]
for tree in intr_tree.tree_list:
intr_tree.replace_tree(tree)
intr_tree.print_element_tree(field_list)
def urljpeg(self):
print("urljpeg - get a jpeg document")
exu = ExerciseUtils()
mysock, url = exu.init_socket_and_url(exu.url_prefix, exu.url_base,
self.url_jpg)
assert mysock is not None
pic = exu.get_jpeg(mysock, url)
assert len(pic) == 230608
mysock = exu.close_socket(mysock) # normal socket
piclen = exu.save_picture(pic, self.local_jpg)
assert piclen > 0
from utils import ExerciseUtils
def_url = "http://data.pr4e.org/mbox-short.txt"
print(
"urllib1 - World's simplest web browser for any url and displays up to 3000 characters"
)
print(" Format of url must be http(s)://urlbase/page")
print(" Example: " + def_url)
url = input("Enter url to open(" + def_url + "): ")
if url == "":
url = def_url
exu = ExerciseUtils()
url_prefix, url_base, url_page = exu.split_url(url)
if url_base == "" or url_base == None:
print("Bad URL")
else:
char_count = exu.print_page_urllib(url, 3000)
assert char_count == 94626
print("Total characters found:", char_count)
import re
from utils import ExerciseUtils
def_url = "http://data.pr4e.org/romeo.txt"
print("socket1 - World's simplest web browser for any url")
print(" Format of url must be http(s)://urlbase/page")
print(" Example: " + def_url)
url = input("Enter url to open(" + def_url + "): ")
if url == "":
url = def_url
exu = ExerciseUtils()
url_prefix, url_base, url_page = exu.split_url(url)
total_chars = exu.print_page_limit(url_prefix,
url_base,
url_page,
3000,
skipheaders=True) # normal socket
import re
from utils import ExerciseUtils
def_url = "http://data.pr4e.org/mbox-short.txt"
print("socket1 - World's simplest web browser for any url and displays up to 3000 characters")
print(" Format of url must be http(s)://urlbase/page")
print(" Example: " + def_url)
url = input("Enter url to open(" + def_url + "): ")
if url == "":
url = def_url
exu = ExerciseUtils()
url_prefix, url_base, url_page = exu.split_url(url)
if url_base == "" or url_base == None:
print("Bad URL")
else:
print("opening socket to:", url)
mysock, url = exu.init_socket_and_url(url_prefix, url_base, url_page)
if mysock != None:
total_chars = exu.print_page_socket(mysock, url, 3000)
print("Total characters found:", total_chars)
mysock = exu.close_socket(mysock) # normal socket
def urllinks2(self):
print("urllinks2 - Look at the parts of a tag")
exu = ExerciseUtils()
html = exu.get_html(exu.url_default2)
exu.bs4_tags(html, 'a')
def urllinks(self):
print("urllinks - Search for link values within URL page using\
BeatifulSoup to parse html")
exu = ExerciseUtils()
html = exu.get_html(exu.url_default1)
exu.bs4_tags(html, 'a', pflags=[False, True, False, False])
def urlregex(self):
print("urlregex - Search for link values within URL input")
exu = ExerciseUtils()
html = exu.get_html(exu.url_default1)
exu.regexlinks(html)
from utils import ExerciseUtils
print(
'ex_11_02 - Write a program to look for lines of the form: New Revision: 39772 \n \
Extract the number from each of the lines using a regular expression and the findall() method. Compute the average of the numbers and print out the average as an integer.'
)
files = ["mbox.txt", "mbox-short.txt"]
exu = ExerciseUtils()
for file in files:
count, avg = exu.run_findall_avg(file, "^New Revision: ([0-9]+)", True)
print("Found ", str(count),
" Average is " + str(avg) + " for file " + file)
from bs4 import BeautifulSoup
from utils import ExerciseUtils
print(
"urlpara - Search for paragrapsh (tags beginning with <p>) within URL page using BeatifulSoup to parse html"
)
exu = ExerciseUtils()
urls = [exu.url_default1, exu.url_default2, exu.url_default3]
for url in urls:
html = exu.get_html(url)
assert len(html) > 0
tags = exu.bs4_tags(html, "p", [True, False, False, False])
print("Reading: ", url)
print("Number of paragraphs: ", len(tags))
import re
from utils import ExerciseUtils
def_url = "http://data.pr4e.org/romeo.txt"
print("socket1 - World's simplest web browser for any url")
print(" Format of url must be http(s)://urlbase/page")
print(" Example: " + def_url)
url = input("Enter url to open(" + def_url + "): ")
if url == "":
url = def_url
exu = ExerciseUtils()
url_prefix, url_base, url_page = exu.split_url(url)
if url_base == "" or url_base == None:
print("Bad URL")
else:
print("opening socket to:", url)
mysock, url = exu.init_socket_and_url(url_prefix, url_base, url_page)
if mysock != None:
page = exu.get_page(mysock, url)
mysock = exu.close_socket(mysock) # normal socket
assert mysock._closed
from utils import ExerciseUtils
print(
'ex_11_01 - Write a simple program to simulate the operation of the grep command on Unix. Ask the user to enter a regular expression and count the number of lines that matched the regular expression'
)
regex_list = list()
regex = input("Enter a regular expression: ")
regex_list.append(regex)
if len(regex_list) > 0:
regex_list = ["^Author", "^X-", "java$"]
exu = ExerciseUtils()
for regex in regex_list:
count = exu.run_search1('mbox.txt', regex, False)
from utils import ExerciseUtils
print("re01 - Search for lines that contain 'From'")
exu = ExerciseUtils()
count = exu.run_search1('mbox-short.txt', 'From:', False)
assert count == 27
print("re02 - Search for lines that start with 'From'")
exu = ExerciseUtils()
count = exu.run_search1('mbox-short.txt', '^From:', False)
assert count == 27
print(
"re03 - Search for lines that start with 'F', followed by 2 characters, followed by 'm:'"
)
exu = ExerciseUtils()
count = exu.run_search1('mbox-short.txt', '^F..m:', False)
assert count == 27
print("re04 - Search for lines that start with From and have an '@' sign")
exu = ExerciseUtils()
count = exu.run_search1('mbox-short.txt', '^From:.+@', False)
assert count == 27
print("re05 - Search for an address")
exu = ExerciseUtils()
count = exu.run_findall('mbox-short5.txt', '\\S+@\\S+', False)
assert count == 5
print("re06 - Search for lines that have an at sign between characters")
exu = ExerciseUtils()