Python web crawler using BeautifulSoup, trouble getting URLs - python-2.7

Question

so I am trying to build a dynamic web crawler to get all url links within links.
so far i am able to get all the links for Chapters, but when I trying to do section links from each chapter, my output does not print out anything.
the code i used :
#########################Chapters#######################
import requests
from bs4 import BeautifulSoup, SoupStrainer
import re
base_url = "http://law.justia.com/codes/alabama/2015/title-{title:01d}/"
for title in range (1,4):
url = base_url.format(title=title)
r = requests.get(url)
for link in BeautifulSoup((r.content),"html.parser",parse_only=SoupStrainer('a')):
if link.has_attr('href'):
if 'chapt' in link['href']:
href = "http://law.justia.com" + link['href']
leveltwo(href)
#########################Sections#######################
def leveltwo(item_url):
r = requests.get(item_url)
soup = BeautifulSoup((r.content),"html.parser")
section = soup.find('div', {'class': 'primary-content' })
for sublinks in section.find_all('a'):
sectionlinks = sublinks.get('href')
print (sectionlinks)

Answer 1

With some minor modifications to your code, I was able to get it to run and output the sections. Mainly, you needed to fix your indentation, and define a function before you call it.
#########################Chapters#######################
import requests
from bs4 import BeautifulSoup, SoupStrainer
import re
def leveltwo(item_url):
r = requests.get(item_url)
soup = BeautifulSoup((r.content),"html.parser")
section = soup.find('div', {'class': 'primary-content' })
for sublinks in section.find_all('a'):
sectionlinks = sublinks.get('href')
print (sectionlinks)
base_url = "http://law.justia.com/codes/alabama/2015/title-{title:01d}/"
for title in range (1,4):
url = base_url.format(title=title)
r = requests.get(url)
for link in BeautifulSoup((r.content),"html.parser",parse_only=SoupStrainer('a')):
try:
if 'chapt' in link['href']:
href = "http://law.justia.com" + link['href']
leveltwo(href)
else:
continue
except KeyError:
continue
#########################Sections#######################
output:
/codes/alabama/2015/title-3/chapter-1/section-3-1-1/index.html
/codes/alabama/2015/title-3/chapter-1/section-3-1-2/index.html
/codes/alabama/2015/title-3/chapter-1/section-3-1-3/index.html
/codes/alabama/2015/title-3/chapter-1/section-3-1-4/index.html etc.

Answer 2

You don't need any try/except blocks, you can use href=True with find or find_all to only select the anchor tags with href's or a css select a[href] as below, the chapter links are in the first ul with inside the article tag with the id #maincontent so you don't need to filter at all:
base_url = "http://law.justia.com/codes/alabama/2015/title-{title:01d}/"
import requests
from bs4 import BeautifulSoup
def leveltwo(item_url):
r = requests.get(item_url)
soup = BeautifulSoup(r.content, "html.parser")
section_links = [a["href"] for a in soup.select('div .primary-content a[href]')]
print (section_links)
for title in range(1, 4):
url = base_url.format(title=title)
r = requests.get(url)
for link in BeautifulSoup(r.content, "html.parser").select("#maincontent ul:nth-of-type(1) a[href]"):
href = "http://law.justia.com" + link['href']
leveltwo(href)
If you were to use find_all you simply need to pass find_all(.., href=True) to filter your anchor tags to only select ones that have hrefs.