According to the book Web Scraping with Python by Ryan Mitchell, he used re.compile. Can anyone explain what is the use of re.compile() at this case, and the content in the re.compile()
code is written in python 3
from urllib.request import urlopen
from bs4 import BeautifulSoup
import re
pages = set()
def getLinks(pageUrl):
global pages
html = urlopen("http://en.wikipedia.org"+pageUrl)
bsObj = BeautifulSoup(html)
for link in bsObj.findAll("a", href=re.compile("^(/wiki/)")):
if 'href' in link.attrs:
if link.attrs['href'] not in pages:
#We have encountered a new page
newPage = link.attrs['href']
print(newPage)
pages.add(newPage)
getLinks(newPage)
getLinks("")