add docstrings
This commit is contained in:
@@ -41,15 +41,24 @@ class WebPage(object):
|
|||||||
|
|
||||||
|
|
||||||
def get_source(self):
|
def get_source(self):
|
||||||
|
'''
|
||||||
|
Retrieve a page's source.
|
||||||
|
'''
|
||||||
|
|
||||||
request = urllib.request.Request(self.url, headers=self.headers)
|
request = urllib.request.Request(self.url, headers=self.headers)
|
||||||
page = urllib.request.urlopen(request)
|
page = urllib.request.urlopen(request)
|
||||||
self.source = page.read()
|
self.source = page.read()
|
||||||
|
|
||||||
|
|
||||||
def find_links(self):
|
def find_links(self):
|
||||||
|
'''
|
||||||
|
Find all URLs on a page and ensure they are absolute. If they are
|
||||||
|
relative then they will be appended to the base URL.
|
||||||
|
'''
|
||||||
|
hrefs = set()
|
||||||
|
|
||||||
soup = BeautifulSoup(self.source, 'html.parser')
|
soup = BeautifulSoup(self.source, 'html.parser')
|
||||||
links = soup.find_all('a')
|
links = soup.find_all('a')
|
||||||
hrefs = set()
|
|
||||||
|
|
||||||
for link in links:
|
for link in links:
|
||||||
if link['href'].startswith('/'):
|
if link['href'].startswith('/'):
|
||||||
@@ -61,6 +70,11 @@ class WebPage(object):
|
|||||||
|
|
||||||
|
|
||||||
def parse_urls(self):
|
def parse_urls(self):
|
||||||
|
'''
|
||||||
|
Iterate through the list of discovered URLs and add them to the
|
||||||
|
pool if they start with the base URL.
|
||||||
|
'''
|
||||||
|
|
||||||
self.urls_to_crawl = set()
|
self.urls_to_crawl = set()
|
||||||
for url in self.discovered_hrefs:
|
for url in self.discovered_hrefs:
|
||||||
if url.startswith(self.url):
|
if url.startswith(self.url):
|
||||||
|
|||||||
Reference in New Issue
Block a user