本文整理汇总了Python中mechanize.urlopen函数的典型用法代码示例。如果您正苦于以下问题:Python urlopen函数的具体用法?Python urlopen怎么用?Python urlopen使用的例子?那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了urlopen函数的20个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Python代码示例。
示例1: slurp_with_login_and_pwd
def slurp_with_login_and_pwd():
import sys
import mechanize
# sys.path.append('ClientCookie-1.0.3')
# from mechanize import ClientCookie
# sys.path.append('ClientForm-0.1.17')
# import ClientForm
# Create special URL opener (for User-Agent) and cookieJar
cookieJar = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookieJar))
opener.addheaders = [("User-agent","Mozilla/5.0 (compatible)")]
mechanize.install_opener(opener)
fp = mechanize.urlopen("http://login.yahoo.com")
forms = mechanize.ParseResponse(fp)
fp.close()
# print forms on this page
for form in forms:
print "***************************"
print form
form = forms[0]
form["login"] = "yahoo-user-id" # use your userid
form["passwd"] = "password" # use your password
fp = mechanize.urlopen(form.click())
fp.close()
fp = mechanize.urlopen("https://class.coursera.org/ml-003/lecture/download.mp4?lecture_id=1") # use your group
fp.readlines()
fp.close()
开发者ID:yz-,项目名称:ut,代码行数:31,代码来源:slurping.py
示例2: main
def main(self):
keyword = remove_polish(word)
openable = 1
response = urlopen(uri)
forms = ParseResponse(response, backwards_compat=False)
if len(forms)==0:
os.system("python PyCrawler.py"+" baza.db '"+ uri+"' 1 "+ keyword)
return
form = forms[0]
# search for text input in form and put keyword there
control = form.find_control(type="text")
control.value = keyword
# form.click() returns a mechanize.Request object
# (see HTMLForm.click.__doc__ if you want to use only the forms support, and
# not the rest of mechanize)
request2 = form.click() # mechanize.Request object
try:
response2 = urlopen(request2)
except:
print "Nie mozna otworzyc formularza"
openable = 0
pass
#get the url of page
if not openable:
search_url=uri
else:
search_url = response2.geturl()
#start crawler on it
os.system("python PyCrawler.py"+" baza.db '"+ search_url+"' 1 "+ keyword)
开发者ID:aras0,项目名称:porownywarka-ofert,代码行数:34,代码来源:formManager.py.py
示例3: _get_results
def _get_results(form, dbg = False):
# click the form
clicked_form = form.click()
# then get the results page
result = mechanize.urlopen(clicked_form)
#### EXPORTING RESULTS FILE
# so what I do is that I fetch the first results page,
# click the form/link to get all hits as a colon separated
# ascii table file
# get the form
resultform = mechanize.ParseResponse(result, backwards_compat=False)
result.close()
resultform = resultform[0]
# set colon as dilimeter of the table (could use anything I guess)
#~ resultform.find_control('export_delimiter').items[1].selected = True
resultform.find_control('export_delimiter').toggle('colon')
resultform_clicked = resultform.click()
result_table = mechanize.urlopen(resultform_clicked)
data = result_table.read()
result_table.close()
if dbg:
return resultform, result_table, data
else:
return data
开发者ID:CadenArmstrong,项目名称:astroquery,代码行数:26,代码来源:core.py
示例4: reply_to
def reply_to(self, postid, message):
params = urllib.urlencode({
'post_parent_id': postid,
'snId': 0,
'post_text': message
})
mechanize.urlopen(self.base_url + "/actions/post.php", params)
开发者ID:zacharydenton,项目名称:BoredAtBot,代码行数:7,代码来源:BoredAtBot.py
示例5: login
def login(self, username, password):
response = urlopen(urljoin(self.uri, "/?cs=login"))
forms = ParseResponse(response, backwards_compat=False)
form = forms[0]
form.set_value(username, name='username')
form.set_value(password, name='password')
self.page = urlopen(form.click())
开发者ID:Sir-Henry-Curtis,项目名称:Ironworks,代码行数:7,代码来源:showRSS.py
示例6: getDLurl
def getDLurl(self, url):
try:
content = self.getUrl(url)
match = re.findall('flashvars.playlist = \'(.*?)\';', content)
if match:
for url in match:
url = 'http://ua.canna.to/canna/'+url
content = self.getUrl(url)
match = re.findall('<location>(.*?)</location>', content)
if match:
for url in match:
url = 'http://ua.canna.to/canna/'+url
req = mechanize.Request('http://ua.canna.to/canna/single.php')
response = mechanize.urlopen(req)
req = mechanize.Request(url)
req.add_header('User-Agent', ' Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3')
response = mechanize.urlopen(req)
response.close()
code=response.info().getheader('Content-Location')
url='http://ua.canna.to/canna/avzt/'+code
print url
return url
except urllib2.HTTPError, error:
printl(error,self,"E")
message = self.session.open(MessageBox, ("Fehler: %s" % error), MessageBox.TYPE_INFO, timeout=3)
return False
开发者ID:Wuschi6,项目名称:MediaPortal,代码行数:27,代码来源:cannalink.py
示例7: get_vorlage
def get_vorlage(session_id, url):
try:
response = mechanize.urlopen(mechanize.Request(url))
pprint.pprint(response)
except URLError:
return
forms = mechanize.ParseResponse(response, backwards_compat=False)
for form in forms:
# All forms are iterated. Might not all be attachment-related.
for control in form.controls:
if control.name == 'DT':
print control.name, control.value
request2 = form.click()
try:
response2 = mechanize.urlopen(request2)
form_url = response2.geturl()
if "getfile.asp" in form_url:
#print "ERFOLG:", response2.info()
pdf = response2.read()
md5 = hashlib.md5(pdf).hexdigest()
scraperwiki.sqlite.save(
unique_keys=['session_id', 'dt', 'md5', 'size'],
data={'session_id': session_id, 'dt': control.value, 'md5': md5, 'size': len(pdf)})
continue
except mechanize.HTTPError, response2:
print "HTTP-FEHLER :("
except URLError:
pass
开发者ID:flyeven,项目名称:scraperwiki-scraper-vault,代码行数:28,代码来源:sessionnet_4_poc.py
示例8: loginRedmine
def loginRedmine():
forms = ParseResponse(urlopen(URL_LOGIN))
form = forms[0]
form['username'] = USER_ID
form['password'] = USER_PW
request = form.click()
mechanize.urlopen(request)
开发者ID:mjkim92,项目名称:ScriptBox,代码行数:7,代码来源:ExportRedmineIssuesToHtml.py
示例9: connect
def connect(url, username, password):
try:
if connected(url):
raise LinkException('You are already connected')
try:
response = urlopen(url)
except URLError:
raise SSIDException('You are not connected on a FON box')
forms = ParseResponse(response, backwards_compat=False)
try:
form = forms[0]
form["login[user]"] = username
form["login[pass]"] = password
except IndexError:
raise SSIDException('You are not connected on a FON box')
try:
response_page = urlopen(form.click()).read()
except NameError:
raise SSIDException('You are not connected on a FON box')
return not 'class="form_error"' in response_page
except PlainURLError:
if connected(url):
return True
else:
raise RuntimeError("Connection failed.")
开发者ID:C4ptainCrunch,项目名称:fon-connect,代码行数:29,代码来源:fon.py
示例10: __get_csv
def __get_csv(self, letter='a', now=False):
#open the url
current_url = self.overview_url + '1111&b=' + letter
overview_req = mechanize.Request(current_url)
overview_res = mechanize.urlopen(overview_req)
#find the list of entries to post
py_query = PyQuery(overview_res.read())
titlelist = py_query("input[name='titelnrliste']").val()
#create the post request
post_data = {
'url': current_url,
'download': '[Download]',
'titelnrliste': titlelist
}
if (now):
#find the checked box (the current quartal)
default_quartal = py_query(".quartal input:checked").attr('name')
post_data[str(default_quartal)] = 'ON'
else:
#enable all quartal's checkbox
quartals = [1, 2, 3, 4]
for i in quartals:
if i in range(1, 5):
post_data[str(self.year) + str(i)] = 'ON'
#send the post request
csv_req = mechanize.Request(current_url, urllib.urlencode(post_data))
csv_res = mechanize.urlopen(csv_req)
self.csv_parser.process_result(response=csv_res)
开发者ID:g-div,项目名称:ivw-viz,代码行数:33,代码来源:ivw.py
示例11: rtnHTMLformat
def rtnHTMLformat(tmpddGenrcgenPresent, sppPrefx, pthwcod, ouPthwpng):
inpx = '\n'.join(tmpddGenrcgenPresent) # inpx="ALDH2 color \nALDH3A1 color"
request = mechanize.Request(
"http://www.genome.jp/kegg/tool/map_pathway2.html")
response = mechanize.urlopen(request)
forms = mechanize.ParseResponse(response, backwards_compat=False)
form = forms[0]
form["unclassified"] = inpx
form["org"] = sppPrefx
request2 = form.click()
response2 = mechanize.urlopen(request2)
a = str(response2.read()).split('href="/kegg-bin/show_pathway?')[1]
code = a.split('/')[0] # response2.read()
request = mechanize.Request(
"http://www.genome.jp/kegg-bin/show_pathway?%s/%s.args" % (code, pthwcod)) # request=mechanize.Request("http://www.genome.jp/kegg-bin/show_pathway?%s/%s.args"%('13171478854246','hsa00410'))
response = mechanize.urlopen(request)
forms = mechanize.ParseResponse(response, backwards_compat=False)
form = forms[1]
status = ' NOT '
try:
imgf = str(forms[1]).split('/mark_pathway')[1].split('/')[0]
os.system("wget --quiet http://www.genome.jp/tmp/mark_pathway%s/%s.png -O %s" % (imgf, pthwcod, ouPthwpng))
status = ' '
except:
pass
return 'A pathway image was%ssuccefully produced...' % status
开发者ID:gigascience,项目名称:galaxy-genome-diversity,代码行数:26,代码来源:mkpthwpng.py
示例12: login
def login(conf):
try:
username = conf.username
password = conf.password
request = mechanize.Request('%s/login.php' % conf.website)
response = mechanize.urlopen(request, timeout=conf.timeout)
forms = mechanize.ParseResponse(response)
response.close()
if len(forms) < 3:
return Left('Failed to reach the login page.')
form = forms[2]
form['username'] = username
form['password'] = password
login_request = form.click()
login_response = mechanize.urlopen(login_request, timeout=conf.timeout)
logged_in = login_response.geturl() == ('%s/index.php'
% conf.website)
if not logged_in:
return Left('Failed to log in with these credentials')
except mechanize.HTTPError as resp:
return Left('HTTPError when logging in: %s' % resp)
except Exception as e:
return Left('%s' % e)
if conf.verbose: sys.stdout.write('Logged in as %s\n' % username)
return Right('Logged in as %s' % username)
开发者ID:Fuuzetsu,项目名称:BakaBT-tools,代码行数:31,代码来源:miscutil.py
示例13: test_sending_headers
def test_sending_headers(self):
handler = self._make_request_handler([(200, [], "we don't care")])
req = mechanize.Request("http://localhost:%s/" % handler.port,
headers={'Range': 'bytes=20-39'})
mechanize.urlopen(req)
self.assertEqual(handler.received_headers['Range'], 'bytes=20-39')
开发者ID:Aaron1011,项目名称:oh-mainline,代码行数:7,代码来源:test_urllib2_localnet.py
示例14: login1
def login1(self):
self.brow = mechanize.Browser()
httpHandler = mechanize.HTTPHandler()
httpsHandler = mechanize.HTTPSHandler()
httpHandler.set_http_debuglevel(DEBUG)
self.cookiejar = mechanize.LWPCookieJar()
#self.cookiejar = "Cookie lzstat_uv=34741959842666604402|1786789; Hm_lvt_976797cb85805d626fc5642aa5244ba0=1304534271541; ASPSESSIONIDQCDRAQBB=JHCHINLAHGMAIGBIFMNANLGF; lzstat_ss=2189193215_2_1304564199_1786789; Hm_lpvt_976797cb85805d626fc5642aa5244ba0=1304535401191"
self.opener = mechanize.OpenerFactory(mechanize.SeekableResponseOpener).build_opener(
httpHandler,httpsHandler,
mechanize.HTTPCookieProcessor(self.cookiejar),
mechanize.HTTPRefererProcessor,
mechanize.HTTPEquivProcessor,
mechanize.HTTPRefreshProcessor,
)
self.opener.addheaders = [("User-Agent","Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.2.13) Gecko/20101203 Firefox/3.6.13"),
("From", "")]
#self.opener.addheaders = [(
# "Referer", self.data['postUrl']
# )]
login={}
login['method'] = self.data['method']
login['name'] = self.data['name']
login['pwd'] = self.data['pwd']
loginUrl = self.data['loginUrl']+'?'+urllib.urlencode(login)
print loginUrl
response = mechanize.urlopen("http://esf.soufun.com/")
response = mechanize.urlopen(loginUrl)
print response.read().decode('gb2312')
开发者ID:aviatorBeijing,项目名称:ptpy,代码行数:30,代码来源:post_soufun.py
示例15: generate_script_sieve
def generate_script_sieve(request, group_id):
group = get_object_or_404(Group, id=group_id)
if request.method == 'POST':
if group.always_data_id:
# There is always_data mail id
from mechanize import ParseResponse, urlopen, urljoin
response = urlopen("https://admin.alwaysdata.com/login/")
forms = ParseResponse(response, backwards_compat=False)
login_form = forms[0]
if settings.DEBUG:
print login_form
login_form["email"] = settings.ALWAYS_DATA_ID
login_form["password"] = settings.ALWAYS_DATA_PASSWORD
response = urlopen(login_form.click())
url = 'https://admin.alwaysdata.com/email/%d/' % group.always_data_id
response = urlopen(url)
forms = ParseResponse(response, backwards_compat=False)
if settings.DEBUG:
for form in forms:
print form
try:
email_form = forms[1]
except IndexError:
messages.warning(request, _(u'%(group)s is not bind to alwaysdata yet (wrong password)' %
{'group': group}))
return HttpResponseRedirect(reverse("group-detail", args=[group.pk]))
email_form['sieve_filter'] = request.POST['filter_sieve'].encode('utf-8')
req = email_form.click()
req.add_header("Referer", url)
response = urlopen(req)
messages.success(request, _(u'Alwaysdata has been updated'))
else:
messages.warning(request, _(u'%(group)s is not bind to alwaysdata yet' %
{'group': group}))
return HttpResponseRedirect(reverse("group-detail", args=[group.pk]))
else:
filter_sieve = export_sieve_configuration(group.contacts.all())
context = get_global_context_data(Group, Group._meta.app_label)
context['object_list'] = Group.objects.all()
context['object'] = group
context['filter_sieve'] = filter_sieve
return render_to_response('contact/contact-sieve.html',
context,
context_instance=RequestContext(request))
开发者ID:Natim,项目名称:ionyse-contact,代码行数:59,代码来源:views.py
示例16: test_404
def test_404(self):
expected_response = 'Bad bad bad...'
handler = self._make_request_handler([(404, [], expected_response)])
try:
mechanize.urlopen('http://localhost:%s/weeble' % handler.port)
except mechanize.URLError, f:
pass
开发者ID:Aaron1011,项目名称:oh-mainline,代码行数:8,代码来源:test_urllib2_localnet.py
示例17: get_nyc_legislation
def get_nyc_legislation(): #search_terms=''
book = xlwt.Workbook(encoding='utf-8', style_compression = 0)
sheet = book.add_sheet('Legi', cell_overwrite_ok = True)
row=-1
for items in ['smoking']:
url = r'http://legistar.council.nyc.gov/Legislation.aspx'
request = mechanize.Request(url)
response = mechanize.urlopen(request)
forms = mechanize.ParseResponse(response, backwards_compat=False)
form = forms[0]
response.close()
form['ctl00$ContentPlaceHolder1$txtSearch'] = items
submit_page = mechanize.urlopen(form.click())
soup = BeautifulSoup(submit_page.read())
for link in soup.find_all("a"):
legislation = link.get("href")
try:
if 'LegislationDetail' in legislation:
url_stem = 'http://legistar.council.nyc.gov/'
url2 = "%s%s" % (url_stem, legislation)
request2 = requests.get(url2)
soup2 = BeautifulSoup(request2.content)
type = soup2.find_all("span",{"id":"ctl00_ContentPlaceHolder1_lblType2"})
status = soup2.find_all("span",{"id":"ctl00_ContentPlaceHolder1_lblStatus2"})
print url2
if ((type[0].text == "Resolution" or
type[0].text == "Introduction") and
(status[0].text == "Adopted")):
legislation_title = soup2.find_all("span",{"id":"ctl00_ContentPlaceHolder1_lblName2"})
legislation_date = soup2.find_all("span",{"id":"ctl00_ContentPlaceHolder1_lblOnAgenda2"})
legislation_committee = soup2.find_all("a",{"id":"ctl00_ContentPlaceHolder1_hypInControlOf2"})
legislation_text = soup2.find_all("span",{"class":"st1"})
legi_url, title, date, committee, text = ([] for i in range(5))
row = row + 1
legi_url = url2
for item in legislation_title:
title.append(item.text)
for item in legislation_date:
date.append(item.text)
for item in legislation_committee:
committee.append(item.text)
for item in legislation_text:
text.append(' '+item.text)
legi = [legi_url,title,date,committee,text]
for column, var_observ in enumerate(legi):
sheet.write (row, column, var_observ)
except:
pass
book.save("legislation_data.xls")
开发者ID:mnsd-12gbm,项目名称:nyc_legi,代码行数:58,代码来源:legi_text.py
示例18: install_phpBB
def install_phpBB():
print "installing phpBB..."
#create forum
url = "http://" + ip + "/phpBB3/"
install_url = url + "install/index.php?mode=install&sub="
br = mechanize.Browser()
post = "dbms=mysqli&dbhost=" + ip + "&dbport=" + port + "&dbname=cryptdb_phpbb&dbuser=root&dbpasswd=letmein&table_prefix=phpbb_&admin_name=admin&admin_pass1=letmein&admin_pass2=letmein&[email protected]&[email protected]"
config = mechanize.urlopen(install_url+"config_file", data=post);
br.set_response(config)
post += "&email_enable=1&smtp_delivery=0&smtp_host=&smtp_auth=PLAIN&smtp_user=&smtp_pass=&cookie_secure=0&force_server_vars=0&server_protocol=http://&server_name=18.26.5.16&server_port=80&script_path=/phpBB"
advanced = mechanize.urlopen(install_url+"advanced", data=post);
br.set_response(advanced)
br.select_form(nr=0)
br.submit()
br.select_form(nr=0)
br.submit()
os.system("mv $EDBDIR/../apps/phpBB3/install $EDBDIR/../apps/phpBB3/install2")
print "logging in..."
#login
br.open(url+"ucp.php?mode=login")
br.select_form(nr=1)
br["username"] = "admin"
br["password"] = "letmein"
br.submit()
print "to ACP..."
#authenticate to go to ACP
br.follow_link(text="Administration Control Panel")
br.select_form(nr=1)
i = str(br.form).find("password")
j = str(br.form).find("=)",i)
br[str(br.form)[i:j]] = "letmein"
br.submit()
print "getting permissions page..."
#navigate to group permissions
br.follow_link(text="Permissions")
br.follow_link(text="Groups\xe2\x80\x99 permissions")
#select Newly Registered Users
br.select_form(nr=0)
br["group_id[]"] = ["7"]
br.submit()
#set all permissions to yes
print "setting permissions..."
br.select_form(nr=1)
i = 1
while i > 0:
start = str(br.form).find("setting[7][0][",i)
if (start < 0):
break
end = str(br.form).find("=[",start)
if (end < 0):
break
br[str(br.form)[start:end]] = ["1"]
i = end
br.submit()
开发者ID:Brainiarc7,项目名称:cryptdb,代码行数:56,代码来源:startphpBB.py
示例19: doLogin
def doLogin():
url = "https://awesome-hd.net/login.php"
response = mechanize.urlopen(url)
forms = mechanize.ParseResponse(response, backwards_compat=False)
form = forms[0]
form["username"] = s.username
form["password"] = s.password
mechanize.urlopen(form.click())
开发者ID:askielboe,项目名称:awesome_downloader,代码行数:10,代码来源:awesome_downloader.py
示例20: isThereInternet
def isThereInternet(self):
try:
mechanize.urlopen('http://github.com', timeout=1)
return True
except mechanize.URLError as e:
print "There is no internet {}".format(e)
self.error_msg.setText("You are not connected to the internet")
self.error_msg.setDetailedText("This feature will not work without an internet connection. ")
self.error_msg.exec_()
return False
开发者ID:georgetk1996,项目名称:Resetter,代码行数:11,代码来源:EasyRepo.py
注:本文中的mechanize.urlopen函数示例由纯净天空整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论