This is the code snippet:
for i in obj:
url = "someurl" + i
oars = requests.get(url, timeout=1)
soup = BeautifulSoup(oars.content)
fout = open(i + ".html", "wt")
print((type(soup.prettify)))
fout.write(oars.text)
oars.close
#fout.write(soup.get_text())
# Still not working, using zsh for now
if call("html2text " + i + ".html" + ">" + i + ".txt", shell=True) == 0:
print("yay")
#call("rm -f " + i + ".html", shell=True)
else:
print(i)
But html2text is just creating empty txt files rather than properly piping the output.
I even tried replacing html2text
with elinks -dump
but to no avail.
Not sure, but this might be what you're after
import subprocess
import sys
outfile = i + ".txt"
cmd = sys.path[0] + "/htmltotext " + i + ".html"
with open(outfile, "w") as output_f:
p = subprocess.Popen(cmd, stdout=output_f, shell=True)