Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commite345db7

Browse files
committed
add selects and textareas in form extraction & submission tutorial
1 parent52cb6d0 commite345db7

File tree

2 files changed

+63
-5
lines changed

2 files changed

+63
-5
lines changed

‎web-scraping/extract-and-fill-forms/form_extractor.py‎

Lines changed: 35 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,9 @@ def get_form_details(form):
2121
including action, method and list of form controls (inputs, etc)"""
2222
details= {}
2323
# get the form action (requested URL)
24-
action=form.attrs.get("action").lower()
24+
action=form.attrs.get("action")
25+
ifaction:
26+
action=action.lower()
2527
# get the form method (POST, GET, DELETE, etc)
2628
# if not specified, GET is the default in HTML
2729
method=form.attrs.get("method","get").lower()
@@ -36,6 +38,38 @@ def get_form_details(form):
3638
input_value=input_tag.attrs.get("value","")
3739
# add everything to that list
3840
inputs.append({"type":input_type,"name":input_name,"value":input_value})
41+
forselectinform.find_all("select"):
42+
# get the name attribute
43+
select_name=select.attrs.get("name")
44+
# set the type as select
45+
select_type="select"
46+
select_options= []
47+
# the default select value
48+
select_default_value=""
49+
# iterate over options and get the value of each
50+
forselect_optioninselect.find_all("option"):
51+
# get the option value used to submit the form
52+
option_value=select_option.attrs.get("value")
53+
ifoption_value:
54+
select_options.append(option_value)
55+
ifselect_option.attrs.get("selected"):
56+
# if 'selected' attribute is set, set this option as default
57+
select_default_value=option_value
58+
ifnotselect_default_valueandselect_options:
59+
# if the default is not set, and there are options, take the first option as default
60+
select_default_value=select_options[0]
61+
# add the select to the inputs list
62+
inputs.append({"type":select_type,"name":select_name,"values":select_options,"value":select_default_value})
63+
fortextareainform.find_all("textarea"):
64+
# get the name attribute
65+
textarea_name=textarea.attrs.get("name")
66+
# set the type as textarea
67+
textarea_type="textarea"
68+
# get the textarea value
69+
textarea_value=textarea.attrs.get("value","")
70+
# add the textarea to the inputs list
71+
inputs.append({"type":textarea_type,"name":textarea_name,"value":textarea_value})
72+
3973
# put everything to the resulting dictionary
4074
details["action"]=action
4175
details["method"]=method

‎web-scraping/extract-and-fill-forms/form_submitter.py‎

Lines changed: 28 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,4 @@
11
frombs4importBeautifulSoup
2-
fromrequests_htmlimportHTMLSession
32

43
frompprintimportpprint
54
fromurllib.parseimporturljoin
@@ -10,25 +9,50 @@
109

1110
# get the URL from the command line
1211
url=sys.argv[1]
12+
all_forms=get_all_forms(url)
1313
# get the first form (edit this as you wish)
14-
first_form=get_all_forms(url)[0]
14+
# first_form = get_all_forms(url)[0]
15+
fori,finenumerate(all_forms,start=1):
16+
form_details=get_form_details(f)
17+
print(f"{i} #")
18+
pprint(form_details)
19+
print("="*50)
20+
21+
choice=int(input("Enter form indice: "))
1522
# extract all form details
16-
form_details=get_form_details(first_form)
23+
form_details=get_form_details(all_forms[choice-1])
1724
pprint(form_details)
1825
# the data body we want to submit
1926
data= {}
2027
forinput_taginform_details["inputs"]:
2128
ifinput_tag["type"]=="hidden":
2229
# if it's hidden, use the default value
2330
data[input_tag["name"]]=input_tag["value"]
31+
elifinput_tag["type"]=="select":
32+
fori,optioninenumerate(input_tag["values"],start=1):
33+
# iterate over available select options
34+
ifoption==input_tag["value"]:
35+
print(f"{i} #{option} (default)")
36+
else:
37+
print(f"{i} #{option}")
38+
choice=input(f"Enter the option for the select field '{input_tag['name']}' (1-{i}): ")
39+
try:
40+
choice=int(choice)
41+
except:
42+
# choice invalid, take the default
43+
value=input_tag["value"]
44+
else:
45+
value=input_tag["values"][choice-1]
46+
data[input_tag["name"]]=value
2447
elifinput_tag["type"]!="submit":
2548
# all others except submit, prompt the user to set it
2649
value=input(f"Enter the value of the field '{input_tag['name']}' (type:{input_tag['type']}): ")
2750
data[input_tag["name"]]=value
51+
2852

2953
# join the url with the action (form request URL)
3054
url=urljoin(url,form_details["action"])
31-
55+
# pprint(data)
3256
ifform_details["method"]=="post":
3357
res=session.post(url,data=data)
3458
elifform_details["method"]=="get":

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp