I'd like to save a webpage for offline viewing, exactly like when you do it from Firefox's menu File > Save Page As ... which saves complete webpage, with all static content in a subfolder.
I found the code below from one of stack overflow answers. When I run it, it downloads a portion of the page, but does not finish completely. I've compared it with what Firefox has downloaded and I see that FF does a better job of saving almost complete webpage.
So what is the best way to download a complete webpage (just the main level, not following the links), along with the necessary static content (css, js, other html)?
I've also seen some suggest to use Selenium in python. But it doesn't work for me as I intend to do this for a large number of pages.
Thanks in advance!
def saveFullHtmlPage(url, pagepath='page', session=requests.Session(), html=None):
"""Save web page html and supported contents
* pagepath : path-to-page
It will create a file `'path-to-page'.html` and a folder `'path-to-page'_files`
"""
def savenRename(soup, pagefolder, session, url, tag, inner):
if not os.path.exists(pagefolder): # create only once
os.mkdir(pagefolder)
for res in soup.findAll(tag): # images, css, etc..
if res.has_attr(inner): # check inner tag (file object) MUST exists
try:
filename, ext = os.path.splitext(os.path.basename(res[inner])) # get name and extension
filename = re.sub('\W+', '', filename) + ext # clean special chars from name
fileurl = urljoin(url, res.get(inner))
filepath = os.path.join(pagefolder, filename)
# rename html ref so can move html and folder of files anywhere
res[inner] = os.path.join(os.path.basename(pagefolder), filename)
if not os.path.isfile(filepath): # was not downloaded
with open(filepath, 'wb') as file:
filebin = session.get(fileurl)
file.write(filebin.content)
except Exception as exc:
print(exc, file=sys.stderr)
if not html:
html = session.get(url).text
soup = BeautifulSoup(html, "html.parser")
path, _ = os.path.splitext(pagepath)
pagefolder = path+'_files' # page contents folder
tags_inner = {'img': 'src', 'link': 'href', 'script': 'src'} # tag&inner tags to grab
for tag, inner in tags_inner.items(): # saves resource files and rename refs
savenRename(soup, pagefolder, session, url, tag, inner)
with open(path+'.html', 'wb') as file: # saves modified html doc
file.write(soup.prettify('utf-8'))