import urllib2, cookielib
import ClientForm
from BeautifulSoup import BeautifulSoup
first_name = "Mona"
la开发者_开发技巧st_name = "Sahlin"
url = 'http://www.ratsit.se/BC/Search.aspx'
cookiejar = cookielib.LWPCookieJar()
cookiejar = urllib2.HTTPCookieProcessor(cookiejar)
opener = urllib2.build_opener(cookiejar)
urllib2.install_opener(opener)
response = urllib2.urlopen(url)
forms = ClientForm.ParseResponse(response, backwards_compat=False)
#Use to print out forms if website design changes
for x in forms:
print x
'''
forms print result:
<aspnetForm POST http://www.ratsit.se/BC/Search.aspx application/x-www-form-urlencoded <HiddenControl(__VIEWSTATE=/wEPDwULLTExMzU2NTM0MzcPZBYCZg9kFgICAxBkZBYGAgoPDxYCHghJbWFnZVVy....E1haW4kZ3J2U2VhcmNoUmVzdWx0D2dkBRdjdGwwMCRtdndVc2VyTG9naW5MZXZlbA8PZGZkle2yQ/dc9eIGMaQPJ/EEJs899xE=) (readonly)>
<TextControl(ctl00$cphMain$txtFirstName=)>
<TextControl(ctl00$cphMain$txtLastName=)>
<TextControl(ctl00$cphMain$txtBirthDate=)>
<TextControl(ctl00$cphMain$txtAddress=)>
<TextControl(ctl00$cphMain$txtZipCode=)>
<TextControl(ctl00$cphMain$txtCity=)>
<TextControl(ctl00$cphMain$txtKommun=)>
<CheckboxControl(ctl00$cphMain$chkExaktStavning=[on])> <ImageControl(ctl00$cphMain$cmdButton=)>
>
'''
#Confirm correct form
form = forms[0]
print form.__dict__
#print form.__dict__.get('controls')
controls = form.__dict__.get('controls')
print "------------------------------------------------------------"
try:
controls[1] = first_name
controls[2] = last_name
page = urllib2.urlopen(form.click('ctl00$cphMain$cmdButton')).read()
''' give error here: The following error occured: "'str' object has no attribute 'name'" '''
# print controls[9]
print '----------here-------'
soup = BeautifulSoup(''.join(page))
soup = soup.prettify()
Here's a working version:
import urllib2, cookielib
import ClientForm
from BeautifulSoup import BeautifulSoup
first_name = "Mona"
last_name = "Sahlin"
url = 'http://www.ratsit.se/BC/Search.aspx'
cookiejar = cookielib.LWPCookieJar()
cookiejar = urllib2.HTTPCookieProcessor(cookiejar)
opener = urllib2.build_opener(cookiejar)
urllib2.install_opener(opener)
response = urllib2.urlopen(url)
forms = ClientForm.ParseResponse(response, backwards_compat=False)
# Use to print out forms to check if website design changes
for i, x in enumerate(forms):
print 'Form[%d]: %r, %d controls' % (i, x.name, len(x.controls))
for j, c in enumerate(x.controls):
print ' ', j, c.__class__.__name__,
try: n = c.name
except AttributeError: n = 'NO NAME'
print repr(n)
#Confirm correct form
form = forms[0]
controls = form.__dict__.get('controls')
print controls, form.controls
print "------------------------------------------------------------"
try:
controls[1].value = first_name
controls[2].value = last_name
p = form.click('ctl00$cphMain$cmdButton')
print 'p is', repr(p)
page = urllib2.urlopen(p).read()
''' give error here: The following error occured: "'str' object has no attribute 'name'" '''
# print controls[9]
print '----------here-------'
soup = BeautifulSoup(''.join(page))
soup = soup.prettify()
finally:
print 'ciao!'
The core bug fix (beyond completing a try statement which you probably truncated, to fix the syntax error) is to use
controls[1].value = first_name
controls[2].value = last_name
in lieu of your buggy code which just assigned directly to controls[1]
and controls[2]
. That bug of yours was what erroneously put strings in the controls
list in lieu of controls (and thus made the by-name search in form.click
fail as you observed).
精彩评论