Python3で超適当なフォームとリンク情報の取得
----------------------------------------------------------------------------------
from urllib.request import urlopen
from bs4 import BeautifulSoup
html = urlopen("http://yahoo.co.jp")
bsObj = BeautifulSoup(html.read())
# Fromの情報を取得
for form_tag in bsObj.body.findAll("form"):
print("SEND URL : {action}".format(action = form_tag.attrs.get("action",None)))
print("METHOD : {method}".format(method = form_tag.attrs.get("method",None)))
print("ENCTYPE : {enctype}".format(enctype = form_tag.attrs.get("enctype",None)))
for input_tag in form_tag.findAll("input"):
print("INPUT NAME : {name}".format(name = input_tag.attrs.get("name",None)))
print("INPUT VALUE : {value}".format(value = input_tag.attrs.get("value",None)))
print("INPUT TYPE : {type}".format(type = input_tag.attrs.get("type",None)))
for text_tag in form_tag.findAll("text"):
print("TEXT NAME : {name}".format(name = text_tag.attrs.get("name",None)))
print("TEXT VALUE : {value}".format(value = text_tag.get_text()))
# Aタグの情報を取得
for a_tag in bsObj.body.findAll("a"):
print("SEND URL : {url}".format(url = a_tag.attrs.get("href",None)))