使用Python的Google表单响应？

Question

我正在尝试编写一个Python脚本，这样就可以在Google表单中提交响应，如下所示： https://docs.google.com/forms/d/152CTd4VY9pRvLfeACOf6SmmtFAp1CL750Sx72Rh6HJ8/viewform

但我如何实际发送的帖子，我如何才能找出，这篇文章应该实际包含什么？

Answer 1

以下是我的剧本：

import urllib
import urllib2

user_agent = 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)'
header={'User-Agent' : user_agent}
url = "http://....Your google form"
# values from your form. You will need to include any hidden variables if you want to..
values= {
'entry.asdfsdfsdasd': 'asdfasdfsd',
'draftResponse':'[,,"-asdfasdasdf"]',
'pageHistory':'0',
'fbzx':'-asdfasdfsd'
}
data = urllib.urlencode(values)
urllib2.Request(url, data, header)

Answer 2

第一个pip install requests

必须将某些特定表单数据发布到特定的url，才能使用请求。表单数据dict params与选项对应，如果不需要某些选项，只需将其从表单数据中删除即可。

import requests
url = 'https://docs.google.com/forms/d/152CTd4VY9pRvLfeACOf6SmmtFAp1CL750Sx72Rh6HJ8/formResponse'
form_data = {'entry.2020959411':'18+ sollte absolute Pflicht sein',
            'entry.2020959411':'Alter sollte garkeine Rolle spielen',
            'entry.2020959411':'17+ wäre für mich vertretbar',
            'entry.2020959411':'16+ wäre für mich vertretbar',
            'entry.2020959411':'15+ wäre für mich vertretbar',
            'entry.2020959411':'Ausnahmen von der Regel - Dafür?',
            'entry.2020959411':'Ausnahmen von der Regel - Dagegen?',
            'entry.2020959411':'__other_option__',
            'entry.2020959411.other_option_response':'test',
            'draftResponse':[],
            'pageHistory':0}
user_agent = {'Referer':'https://docs.google.com/forms/d/152CTd4VY9pRvLfeACOf6SmmtFAp1CL750Sx72Rh6HJ8/viewform','User-Agent': "Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.52 Safari/537.36"}
r = requests.post(url, data=form_data, headers=user_agent)

Answer 3

根据@piggfly的回答，我编写了一个小脚本来获取字段名（仅用于文本字段表单）

import urllib.request
from bs4 import BeautifulSoup
import requests, warnings
def get_questions(in_url):
    res = urllib.request.urlopen(in_url)
    soup = BeautifulSoup(res.read(), 'html.parser')
    get_names = lambda f: [v for k,v in f.attrs.items() if 'label' in k]
    get_name = lambda f: get_names(f)[0] if len(get_names(f))>0 else 'unknown'
    all_questions = soup.form.findChildren(attrs={'name': lambda x: x and x.startswith('entry.')})
    return {get_name(q): q['name'] for q in all_questions}
def submit_response(form_url, cur_questions, verbose=False, **answers):
    submit_url = form_url.replace('/viewform', '/formResponse')
    form_data = {'draftResponse':[],
                'pageHistory':0}
    for v in cur_questions.values():
        form_data[v] = ''
    for k, v in answers.items():
        if k in cur_questions:
            form_data[cur_questions[k]] = v
        else:
            warnings.warn('Unknown Question: {}'.format(k), RuntimeWarning)
    if verbose:
        print(form_data)
    user_agent = {'Referer':form_url,
                  'User-Agent': "Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.52 Safari/537.36"}
    return requests.post(submit_url, data=form_data, headers=user_agent)

然后，您可以使用“获取问题”功能获取可以填写的字段

TEST_FORM_URL = "https://docs.google.com/forms/d/e/1FAIpQLSfBmvqCVeDA7IZP2_mw_HZ0OTgDk2a0JN4VlY5KScECWC-_yw/viewform"

anno_questions = get_questions(TEST_FORM_URL)

把问题（字段）作为听写

{'annotator': 'entry.756364489',
 'task': 'entry.1368373366',
 'item_id': 'entry.84713541',
 'label': 'entry.2072511216',
 'session': 'entry.2021127767',
 'time': 'entry.1122475936'}

然后使用带有关键字参数的submit_响应提交

submit_response(TEST_FORM_URL, anno_questions, annotator="TestUser", item_id = 0)