def main():
br = Browser('chrome')
br.visit(URL)
sleep(3)
if br.is_text_present("Remember me", wait_time=7):
br.fill('username', NAME)
br.fill('password', PASSWORD)
br.execute_script('javascript:savesettings()')
def main():
br = Browser('chrome')
br.visit(URL)
sleep(3)
if br.is_text_present("Remember me", wait_time=7):
br.fill('username', NAME)
br.fill('password', PASSWORD)
br.execute_script('javascript:savesettings()')
def form_fill(user, form):
display = Display(visible=0, size=(800, 600))
display.start()
if form.email != {}:
st = emailFill(user, form)
email_send("Software Internship Application",st,[form.email['email'], user.getField(2)],attachment=user.getField(6))
return
browser = Browser()
browser.visit(form.url)
if form.greenHouseResume:
string = """$("#application_form").append('<input type="hidden" id="resume_url" name="job_application[resume_url]" value=""" + '"' + user.getField(6.1) + '"' + """><input type="hidden" id="resume_url_filename" name="job_application[resume_url_filename]" value="resume.pdf">')"""
browser.execute_script(string)
def doClicks(): #partial_htmls being dealt with
for ele in form.html_button_clicks:
browser.find_link_by_partial_href(ele)[0].click()
def fillField():
for ele, tple in form.Fill_Fields.iteritems():
browser.fill(ele,user.getField(tple[0]))
def attachField():
for ele, field in form.Attach_Fields.iteritems():
browser.attach_file(ele,os.getcwd() + "/" + user.getField(field))
def dropDownField():
for ele, index in form.Drop_Down_Fields.iteritems():
browser.execute_script('document.getElementById("' + ele + '")[' + str(index) + '].selected=true')
def dropDownHelper():
for ele,index in form.Drop_Down_Fields_Helper.iteritems():
browser.execute_script('document.getElementsByTagName("'+ele+'")['+str(index)+'].selected=true')
def checkBoxes():
for ele in form.CheckBoxes:
browser.execute_script('document.getElementById("' + ele + '").checked=true')
def doJS():
for ele in form.extraJavaScript:
browser.execute_script(ele)
def doJSHelp():
for ele, index in form.extraJSHelper.iteritems():
browser.execute_script('document.getElementById("' + ele +'").value = "'+ user.getField(index) +'";')
def submitJS():
for ele in form.submitJS:
browser.execute_script(ele)
doClicks()
fillField()
attachField()
dropDownField()
dropDownHelper()
checkBoxes()
doJS()
doJSHelp()
submitJS()
if not form.submitJS:
browser.execute_script('document.getElementsByClassName("' + form.finalSubmit + '")[document.getElementsByClassName("' + form.finalSubmit + '").length-1].click()')
time.sleep(10)
browser.quit()
display.stop()
class TemMail():
def __init__(self):
self.driver_name = 'chrome'
self.executable_path = '/usr/local/bin/chromedriver'
self.driver = Browser(driver_name=self.driver_name,
executable_path=self.executable_path)
self.driver.driver.set_window_size(800, 800)
self.driver.visit('https://www.moakt.com')
self.driver.find_by_name('random').click()
while self.driver.url == 'https://www.moakt.com/zh/mail':
return
def getMailName(self):
sleep(1)
self.driver.execute_script('changeAddress();')
sleep(1)
mailname = self.driver.find_by_id('email-address').text
return mailname
def getEmail(self):
while True:
self.driver.find_by_text(u"刷新列表").click()
temdata = self.driver.find_by_text(u"激活您的ProcessOn帐号")
if len(temdata) == 0:
sleep(2)
else:
em = self.driver.find_by_text(u"激活您的ProcessOn帐号").first
url = em["href"] + '/content'
self.getEmailDea(url)
break
def getEmailDea(self, emlurl):
self.driver.visit(emlurl)
temtext = self.driver.html
url_verify = re.findall(
r"https://www.processon.com/signup/verification/\w+", temtext)
ss_mail = requests.Session()
rsp_verify = ss_mail.get(url_verify[0])
if rsp_verify.status_code == 200:
self.driver.quit()
else:
print("failure：" + rsp_verify.status_code)
from splinter.browser import Browser
#from time import sleep
b = Browser('firefox')
b.visit('http://www.baidu.com')
#b.fill('wd', 'test\r')
#b.fill('wd', 'test\n')
#b.fill('wd', 'test\r\n')
b.fill('wd', 'test')
#b.execute_script('document.getElementsByName("f")[0].submit()')
script = '''
var e = document.createEvent('KeyboardEvent');
e.initKeyEvent('keypress', true, true, window, false, false, false, false, 13, 0);
document.getElementsByName('wd')[0].dispatchEvent(e);
'''
b.execute_script(script)
#sleep(5)
b.type('wd', ' python')
#b.type('wd', ' python', slowly=True) # slowly not working
def huoche():
global b
b = Browser(driver_name="chrome")
b.visit(ticket_url)
b.execute_script('alert("开始刷票喽~~~~")')
sleep(2)
b.get_alert().dismiss()
while b.is_text_present(u"登录"):
sleep(1)
login()
if b.url == initmy_url:
break
try:
#跳回购票页面
b.visit(ticket_url)
#加载查询信息
b.cookies.add({"_jc_save_fromStation": starts})
b.cookies.add({"_jc_save_toStation": ends})
b.cookies.add({"_jc_save_fromDate": dtime})
b.reload()
i = 1
#循环点击预订
if order != 0:
while b.url == ticket_url:
b.find_by_text(u"查询").click()
# b.find_by_text(ttype).click()
if b.find_by_text(u"预订"):
sleep(0.3)
b.find_by_text(u"预订")[order - 1].click()
print b.url
if b.is_text_present(u"证件号码", wait_time=0.2):
# print [ i.text for i in b.find_by_text(pa) ]
b.find_by_text(pa)[1].click()
else:
b.execute_script('alert("似乎没有可预订选项")')
b.get_alert().dismiss()
pass
else:
while b.url == ticket_url:
b.find_by_text(u"查询").click()
if b.find_by_text(u"预订"):
sleep(0.3)
for i in b.find_by_text(u"预订"):
i.click()
sleep(0.1)
if b.is_text_present(u"证件号码"):
b.find_by_text(pa)[1].click()
else:
b.execute_script('alert("似乎没有可预订选项")')
b.get_alert().dismiss()
pass
b.execute_script('alert("能做的都做了")')
b.get_alert().dismiss()
print u"能做的都做了.....不再对浏览器进行任何操作"
except Exception:
print u"出错了...."
class Amazon(object):
def __init__(self, keyword):
self.url = "https://www.amazon.com"
self.name = "".join(random.sample(string.ascii_letters + string.digits, 6))
self.email = "".join(random.sample(string.ascii_letters + string.digits, 16)) + "@163.com"
self.password = "".join(random.sample(string.ascii_letters + string.digits, 8))
self.keyword = keyword
self.chrome_options = Options()
logging.basicConfig(filename='amazon.log', level=logging.DEBUG)
self.conn = pymysql.connect(host='192.168.0.211', port=6033, user='******', password='******', db='amazon')
self.cs = self.conn.cursor()
self.cs.execute('select id,ip,port from register_proxy_ips where is_alived = 1 order by id desc limit 1')
self.proxy_ip = self.cs.fetchone()
self.cs.execute('update register_proxy_ips set is_alived = 0 where id = %s' % self.proxy_ip[0])
self.conn.commit()
logging.debug(self.proxy_ip)
# self.chrome_options.add_argument('--proxy-server=http://{host}:{port}'.format(host=self.proxy_ip[1], port=self.proxy_ip[2]))
self.browser = Browser('chrome', user_agent=generate_user_agent(device_type='desktop'))
def run(self):
self.acess()
self.search_kw()
i = 1
while i < 7:
ad_list = self.browser.find_by_xpath('//li[contains(@class, "AdHolder")]')
if ad_list:
ad_list[0].find_by_tag('h2').click()
break
else:
time.sleep(300)
self.search_kw()
i += 1
if i > 6:
self.browser.quit()
self.register()
self.add_pay_method()
self.add_address()
self.buy_goods()
self.add_list()
def acess(self):
self.browser.visit(self.url)
logging.error("代理IP失效，请求不成功")
def search_kw(self):
self.browser.find_by_xpath('//input[@id="twotabsearchtextbox"]').first.fill(self.keyword)
self.browser.find_by_xpath('//input[@value="Go"]').click()
draggble = self.browser.find_by_xpath('//*[@id="searchTemplate"]')
target = self.browser.find_by_xpath('//*[@id="footer"]')
draggble.drag_and_drop(target)
# time.sleep(random.randint(1, 6))
def register(self):
self.browser.find_by_xpath('//*[@id="nav-link-accountList"]').click()
self.browser.find_by_xpath('//*[@id="createAccountSubmit"]').click()
self.browser.find_by_xpath('//input[@id="ap_customer_name"]').first.fill(self.name)
self.browser.find_by_xpath('//input[@id="ap_email"]').first.fill(self.email)
self.browser.find_by_xpath('//input[@id="ap_password"]').first.fill(self.password)
self.browser.find_by_xpath('//input[@id="ap_password_check"]').first.fill(self.password)
self.browser.find_by_xpath('//input[@class="a-button-input"]').click()
def add_pay_method(self):
self.browser.find_by_xpath('//*[@id="nav-link-accountList"]').click()
self.browser.find_by_xpath('//*[@id="a-page"]/div[3]/div/div[2]/div[2]/a/div').click()
self.browser.fill('ppw-accountHolderName', paras['card_name'])
self.browser.fill('addCreditCardNumber', paras['card_num'])
self.browser.execute_script('document.getElementsByName("ppw-expirationDate_month")[0].style.display="block"')
self.browser.execute_script('document.getElementsByName("ppw-expirationDate_year")[0].style.display="block"')
self.browser.find_by_text('04').click()
self.browser.find_by_text('2019').click()
self.browser.find_by_name('ppw-widgetEvent:AddCreditCardEvent').click()
def add_address(self):
self.browser.fill('ppw-fullName', paras['fullname'])
self.browser.fill('ppw-line1', paras['line'])
self.browser.fill('ppw-city', paras['city'])
self.browser.fill('ppw-stateOrRegion', paras['stateOrRegion'])
self.browser.fill('ppw-postalCode', paras['postalCode'])
self.browser.fill('ppw-phoneNumber', paras['phoneNumber'])
self.browser.find_by_name('ppw-widgetEvent:AddAddressEvent').click()
def buy_goods(self):
self.browser.find_by_xpath('//*[@id="nav-recently-viewed"]').click()
self.browser.find_by_xpath('//*[@id="asin_list"]/div[1]/div/a/div[1]/span/div').click()
try:
self.browser.find_by_xpath('//*[@id="add-to-cart-button"]').click() # add cart
self.browser.find_by_xpath('//*[@id="smartShelfAddToCartNative"]').click()
except Exception as e:
logging.error(e)
try:
time.sleep(5)
self.browser.is_element_present_by_xpath('//i[@class="a-icon a-icon-close"]', wait_time=30)
self.browser.find_by_xpath('//i[@class="a-icon a-icon-close"]').click()
except Exception:
pass
try:
self.browser.find_by_xpath('//a[@id="hlb-view-cart-announce"]').click() # enter cart
except Exception:
pass
self.browser.execute_script('document.getElementsByName("quantity")[0].style.display="block"')
self.browser.find_by_value('10').click()
self.browser.find_by_name('quantityBox').clear()
self.browser.fill('quantityBox', 999)
self.browser.find_by_xpath('//span[@id="a-autoid-1"]').click()
self.browser.find_by_xpath('//div[@class="sc-proceed-to-checkout"]').click()
self.browser.find_by_xpath('//*[@id="address-book-entry-0"]/div[2]/span/a').click()
self.browser.find_by_xpath('//*[@id="shippingOptionFormId"]/div[3]/div/div/span[1]').click()
self.browser.find_by_xpath('//*[@id="order-summary-container"]/div/div/div').click()
try:
self.browser.find_by_xpath('//a[contains(@class, "prime-nothanks-button")]').click()
except Exception:
pass
self.browser.find_by_xpath('//span[contains(@class, "place-order-button-link")]').click()
def add_list(self):
self.browser.find_by_xpath('//*[@id="nav-recently-viewed"]').click()
self.browser.find_by_xpath('//*[@id="asin_list"]/div[1]/div/a/div[1]/span/div').click()
self.browser.find_by_xpath('//input[@title="Add to List"]').click()
if self.browser.is_element_present_by_text('Add to your list', wait_time=10):
self.browser.find_by_xpath('//*[@id="WLHUC_result"]/form/div[2]/span[3]/span').click()
self.browser.find_by_xpath('//i[@class="a-icon a-icon-close"]').click()
time.sleep(2)
self.browser.quit()
#!usr/bin/python
from splinter.browser import Browser
import re
import time
import sys
import os
SongName=sys.argv[1]
br=Browser('chrome')
br.driver.set_window_size(10,10)
br.visit("http://www.youtube.com")
time.sleep(5)
searchbar=br.find_by_id("masthead-search-terms").first.find_by_tag("input")[0]
searchbar.fill(SongName)
br.execute_script("if (document.getElementById('masthead-search-term').value == '') return false; document.getElementById('masthead-search').submit(); return false;;return true;")
URLfirst=br.find_by_id("results").first.find_by_tag("a")
YoutubeURL=URLfirst[1]['href']
br.quit()
os.system("cd ~/Downloads")
executionstring="youtube-dl -x --extract-audio --audio-format mp3 --audio-quality 0 "+YoutubeURL
os.system(executionstring)
##For Youtube-mp3.org method, uncomment all the lines below. Since I had
##youtube-dl installed on my laptop, I am using a method which has higher quality, but takes
##more time to install
#br.visit("http://www.youtube-mp3.org/")
#URLarea=br.find_by_id("youtube-url").fill(YoutubeURL)
#button=br.find_by_id("submit")
#button.click()
#print "Ready to click"
#time.sleep(10)
class WeiboSpider(object):
page_count = 0 # 记录每个页面抓取的数据量
all_count = 0 # 记录抓取的数据总量
save_data = OrderedDict({ # 保存抓取的数据
"昵称": [],
"微博正文": [],
"微博链接": [],
"时间": [],
"收藏数": [],
"转发数": [],
"评论数": [],
"点赞数": [],
"设备": []
})
xpath_dict = { # 解析数据用的 xpath
'昵称': '//div[@class="info"]//a[@class="name"]/text()',
'微博正文':
'//div[@class="content"]/p[@node-type="feed_list_content"]//text()',
'微博链接': '//div[@class="content"]/p[@class="from"]/a[1]/@href',
'时间': '//div[@class="content"]/p[@class="from"]/a[1]/text()',
'收藏数': '//a[@action-type="feed_list_favorite"]/text()',
'转发数': '//a[@action-type="feed_list_forward"]/text()',
'评论数': '//a[@action-type="feed_list_comment"]/text()',
'点赞数':
'//div[@class="card-act"]//a[@action-type="feed_list_like"]//em/text()',
'设备': '//div[@class="content"]/p/a[@rel="nofollow"]/text()'
}
def __init__(self,
keyword,
start_time,
end_time,
sleep_time=10,
username=None,
password=None):
self.username = username # 微博用户名
self.password = password # 微博密码
self.browser = None
self.browser_name = "firefox" # 浏览器名
self.driver_path = "../driver/firefoxdriver.exe" # 打开浏览器的驱动
self.base_url = "https://s.weibo.com/" # 微博搜索主页
self.search_url = 'https://s.weibo.com/weibo/{keyword}' \
'×cope=custom:{start_time}:{end_time}&refer=g' # 搜索结果的url
self.keyword = keyword # 搜索关键字
self.sleep_time = sleep_time # 点击下一页的时间间隔
self.start_time = start_time # 搜索内容的起始时间
self.end_time = end_time # 搜索内容的结束时间
self.base_sava_path = '../files/' # 输出文件的保存路径
self.save_file_name = self.keyword + self.start_time + "~" + self.end_time # 输出文件名
def refactor_date(self, start_time, end_time): # 构造搜索的起止时间
self.start_time = datetime.strptime(
start_time, "%Y-%m-%d-%H").strftime("%Y-%m-%d-%H")
if end_time:
self.end_time = datetime.strptime(
end_time, "%Y-%m-%d-%H").strftime("%Y-%m-%d-%H")
else:
self.end_time = datetime.now().strftime('%Y-%m-%d-%H')
def get_search_url(self): # 构造搜索url
self.refactor_date(self.start_time, self.end_time) # 将输入的时间重构成搜索用的标准参数
return self.search_url.format(keyword=self.keyword,
start_time=self.start_time,
end_time=self.end_time)
def login(self):
"""
用于登录微博
"""
self.browser = Browser(driver_name=self.browser_name,
executable_path=self.driver_path,
service_log_path='../files/log.log') # 打开浏览器
self.browser.visit(self.base_url) # 访问微博搜索页面
self.browser.click_link_by_text('登录') # 点击登录
# 填充用户名的密码
if self.username is not None:
self.browser.fill("username", self.username)
if self.password is not None:
self.browser.fill("password", self.password)
print("请在打开的浏览器中登录........")
time.sleep(2) # 暂停两秒，等待浏览器加载完成
logining_url = self.browser.url # 获取正在登录时的 url
# 防止网络不好时获取不到正在登录时的 url
while logining_url == self.base_url:
time.sleep(2)
logining_url = self.browser.url
# 通过验证 url 保证已经登录
while 1:
if self.browser.url != logining_url:
break
time.sleep(2)
print("已成功登录，开始抓取信息.......")
def search(self):
"""
通过构造的搜索 url，跳转到搜索结果页面
"""
self.browser.visit(self.get_search_url())
def get_card_data(self, card, xapth_dict: dict):
"""
用户获取每一篇博客的信息
"""
etree_html = etree.HTML(card.html)
number = ['收藏数', '转发数', '评论数', '点赞数']
self.page_count += 1 # 统计每一页抓取的数据量
for key in xapth_dict.keys():
xpath = xapth_dict.get(key)
data = etree_html.xpath(xpath)
if data:
if key in number:
self.save_data[key].append(Utils.get_num(data[0]))
elif key == '时间':
self.save_data[key].append(
Utils.get_date(data[0]).strftime('%Y-%m-%d'))
elif key == '微博正文':
content = ''.join(data).replace(' ', '').replace('\n', '')
self.save_data[key].append(content)
else:
self.save_data[key].append(data[0])
else:
if key in number:
self.save_data[key].append('0')
else:
self.save_data[key].append('')
def download_data(self):
self.browser.execute_script(
"window.scrollTo(0,document.body.scrollHeight)") # 跳转到页面底部
try:
self.browser.click_link_by_text('查看全部搜索结果')
except ElementDoesNotExist:
pass
page_index = 1 # 记录页码
while page_index <= 50: # 微博搜索结果最多为50页
# 获取真实的页码
try:
# 微博搜索结果有时候一直点击下一页，到了最后一页会跳转到第一页
# 这段代码用于防止出现这种情况
real_page = re.findall(r'page=(\d+)', self.browser.url)
if real_page:
real_page = int(real_page[0])
else:
real_page = 1
if real_page < page_index:
break
print('正在抓取第%s页内容：' % page_index, end='')
self.browser.execute_script(
"window.scrollTo(0,document.body.scrollHeight)") # 跳转到页面底部
cards = self.browser.find_by_xpath(
'//div[@class="card"]') # 获取所有的博文
except KeyboardInterrupt: # 如果觉得抓取时间过长，可以按下ctrl c 中止抓取，然后可以保存已抓取的信息
print('中途退出抓取，正则保存中.....')
break
for card in cards: # 遍历所有的文章，获取数据
try:
self.get_card_data(card, self.xpath_dict)
except KeyboardInterrupt:
pass
try:
print('本页抓取了%s条数据，模拟等待中.....' % self.page_count)
self.all_count += self.page_count # 统计获取的所有数据量
self.page_count = 0
# 基于设置的休眠时间，随机设置一个休眠值
sleep_time = random.randint(self.sleep_time,
self.sleep_time + 5)
time.sleep(sleep_time) # 模拟用户浏览网页的时间
try:
self.browser.click_link_by_text('下一页') # 点击下一页
page_index += 1
except ElementDoesNotExist:
break
except KeyboardInterrupt:
print('中途退出抓取，正则保存中.....')
break
def save(self):
"""
保存数据
"""
print('--------------------------------------------')
print('本次共抓取了%s条数据' % self.all_count)
try:
data = pandas.DataFrame(self.save_data)
file_path = self.base_sava_path + self.save_file_name + '.xlsx'
data.to_excel(file_path, index=False) # 将数据保存到 excel
print('文件正在保存...', end='\n\n')
except Exception as e:
print('文件保存失败！！！', end='\n\n')
print(e)
def close(self):
self.browser.quit() # 关闭浏览器
@staticmethod
def test():
"""
用于测试的方法，实际运行时不执行
"""
browser = Browser(executable_path="../driver/firefox.exe")
browser.visit(
"https://s.weibo.com/weibo/%25E5%25B0%25B1%25E5%25"
"BC%2580%25E5%25A7%258B%25E5%25A4%25A7%25E5%25B9%2585?topnav=1&wvr=6&b=1"
)
cards = browser.find_by_xpath('//div[@class="card"]')
for c in cards:
etree_html = etree.HTML(c.html)
a = etree_html.xpath(
'//div[@class="card-act"]//a[@title="赞"]/em/text()')
print(a[0])
def check():
global b
b = Browser(driver_name="chrome")
b.visit(ticket_url)
b.execute_script('alert("开始刷票")')
sleep(2)
b.get_alert().dismiss()
while b.is_text_present(u"登录"):
sleep(1)
login()
if b.url == initmy_url:
break
try:
# 跳回购票页面
b.visit(ticket_url)
# 加载车票查询信息
b.cookies.add({"_jc_save_fromStation":starts})
b.cookies.add({"_jc_save_toStation":ends})
b.cookies.add({"_jc_save_fromDate":dtime})
b.reload()
i = 1
# 循环点击预订
if order != 0:
while b.url == ticket_url:
sleep(3)
b.find_by_text(u"查询").click()
# b.find_by_text(ttype).click()
if b.find_by_text(u"预订"):
sleep(0.3)
b.find_by_text(u"预订")[order - 1].click()
print(b.url)
if b.is_text_present(u"证件号码",wait_time = 0.5):
# print [ i.text for i in b.find_by_text(pa) ]
b.find_by_text(pa)[1].click()
else:
b.execute_script('alert("没有可预订选项")')
b.get_alert().dismiss()
pass
else:
while b.url == ticket_url:
sleep(3)
b.find_by_text(u"查询").click()
if b.find_by_text(u"预订"):
sleep(0.3)
for i in b.find_by_text(u"预订"):
i.click()
sleep(0.1)
if b.is_text_present(u"证件号码"):
b.find_by_text(pa)[1].click()
else:
b.execute_script('alert("似乎没有可预订选项")')
b.get_alert().dismiss()
pass
b.execute_script('alert("能做的都做了")')
b.get_alert().dismiss()
print(u"能做的都做了.....不再对浏览器进行任何操作")
except Exception:
print(u"出错了....")
SongName=raw_input("enter song ")
br=Browser('chrome')
br.driver.set_window_size(10,10)
br.visit("http://www.youtube.com")
time.sleep(5)
searchbar=br.find_by_id("masthead-search-terms").first.find_by_tag("input")[0]
searchbar.fill(SongName)
br.execute_script("document.getElementById('masthead-search').submit();")
URLfirst=br.find_by_id("results").first.find_by_tag("a")
for i in range(1,50):
print i
if (URLfirst[i]['href'].find("watch")!=-1 and len(URLfirst[i]['href'])< 50):
YoutubeURL=URLfirst[i]['href']
break
br.quit()
mp3 = pafy.new(YoutubeURL)
bestaudio = mp3.getbestaudio()
for channel in channels:
# create output file
rawfile = open("data/{}_raw.txt".format(channel), "w+")
parsedfile = open("data/{}_parsed".format(channel), "w+")
browser.visit("https://open.rocket.chat/channel/{}".format(channel))
time.sleep(10)
# scroll up to load previous messages
# i have not figured out a way to detect when the channel is completely loaded
# mostly because i am lazy and it doesnt really matter
# so i just put 300 as a safe number
# if it's too low, increase it. if it's too high (takes too long) decrease it
# in any case it only takes 15 minutes to do 300 scrolls
for i in range(300):
browser.execute_script(
"document.querySelector('.messages-box .wrapper').scrollTo(0, -document.querySelector('.messages-box .wrapper').scrollHeight);"
)
# for scroll loading time because rocket chat is a slow ass piece of shit
time.sleep(3)
# scrape raw file
wrapper = browser.find_by_css('.messages-box .wrapper')
html = BeautifulSoup(wrapper.html, 'html.parser')
# use .replace('\\n', ' ').replace('\\t', '').replace('\\', '') to parse this
rawfile.write(str(html.text.encode('unicode-escape')))
# scrape parsed data
data = []
wrapper = browser.find_by_css('.messages-box .wrapper .message')
i = 0
while True:
def huoche():
global b
b = Browser(driver_name="chrome")
b.visit(ticket_url)
while b.is_text_present(u"登录"):
sleep(1)
login()
if b.url == initmy_url:
break
try:
print u"进入购票页面..."
# 跳回购票页面
b.visit(ticket_url)
# 加载查询信息
b.cookies.add({"_jc_save_fromStation": starts})
b.cookies.add({"_jc_save_toStation": ends})
b.cookies.add({"_jc_save_fromDate": dtime})
b.reload()
b.cookies.all()
sleep(2)
count = 0
# 循环点击预订
if order != 0:
while b.url == ticket_url:
b.find_by_text(u"查询").click()
count += 1
print u"1循环点击查询... 第 %s 次, order=%d" % (count, order)
sleep(10) #in seconds
try:
b.find_by_text(u"预订")[order - 1].click()
sleep(1)
if b.is_text_present(u"证件号码", wait_time=0.5):
b.find_by_text(pa)[1].click()
b.execute_script("alert('请选择验证码并提交订单')")
break
except:
print u"还没开始预订"
continue
else:
while b.url == ticket_url:
b.find_by_text(u"查询").click()
count += 1
#print u"循环点击查询... 第 %s 次" % count
print u"2循环点击查询... 第 %s 次, order=%d" % (count, order)
sleep(10)
try:
for i in b.find_by_text(u"预订"):
i.click()
sleep(1)
if b.is_text_present(u"证件号码"):
b.find_by_text(pa)[1].click()
b.execute_script("alert('请选择验证码并提交订单')")
raise finishreservation()
#break;
except finishreservation:
break
except Exception as e:
print u"还没开始预订"
continue
#sleep(1)
#b.find_by_text(pa)[1].click()
print u"请手动操作...."
except Exception as e:
print(traceback.print_exc())
In this example we will:
- send code to be executed on browser
- manipulate the DOM with javascript code with splinter
- get the data from javascript
NOTE: You will see the example code more advanced and organized in:
javascript_advanced_and_organized_code.py
"""
from splinter.browser import Browser
browser = Browser('chrome')
# Visit URL
url = "http://splinter.cobrateam.info/"
browser.visit(url)
# 1 - Send code to webpage to be executed
# you can execute a simple javascript code
browser.execute_script('alert("Hello World")')
# assign variable
javascript_code = 'message = "After this alert, the body tag will disappear";'
javascript_code += 'alert(message);'
browser.execute_script(javascript_code)
# you just can execute any javascript code, like,
# for example, manupulate dom
# javascript snippet to hidden the body
browser.execute_script('document.getElementsByTagName("body")[0].style.display = "none"')
# 2 - Getting data returned from javascript code execution
# getting value of the 'display' attribute from the body tag
value_of_display = browser.evaluate_script('document.getElementsByTagName("body")[0].style.display')
browser.execute_script('alert("As you could see, the body disappeared, so the display is set as: %s");' % value_of_display)
browser.execute_script('alert("..but now");')
# back to the normal, that is, display:block
browser.execute_script('document.getElementsByTagName("body")[0].style.display = "block"')
#!usr/bin/python
from splinter.browser import Browser
import re
import time
br=Browser()
br.visit("http://www.160by2.com/Index")
br.fill('username','YOUR_PHONE_NUMBER_USED_TO_CREATE_160BY2_ACCOUNT')
br.fill('password','YOUR_ACCOUNT_PASSWORD')
button = br.find_by_name("")
button.click()
stringurl=br.url
stringurl2=stringurl.split("id=",1)[1]
id=stringurl2.split("id=",1)[1]
jsstring="window.parent.openPage('SendSMS?id="+id+"', 'aSendSMS', 'aSMS', 'ulSMS')"
br.execute_script(jsstring)
time.sleep(8)
br.execute_script(jsstring)
print "JS Executed"
time.sleep(8)
with br.get_iframe('by2Frame') as iframe:
iframe.fill("sendSMSMsg","Well, I guess robot's do send SMSes when spandan wants them to ;)")
iframe.find_by_tag("input")[10].fill("THE_PHONE_NUMBER_YOU_WANT_TO_SEND_SMS_TO")
button2=iframe.find_by_id("btnsendsms").first
print button2.value
button2.click()
from splinter.browser import Browser
import re
import time
br = Browser()
br.visit("http://www.160by2.com/Index")
br.fill('username', 'YOUR_PHONE_NUMBER_USED_TO_CREATE_160BY2_ACCOUNT')
br.fill('password', 'YOUR_ACCOUNT_PASSWORD')
button = br.find_by_name("")
button.click()
stringurl = br.url
stringurl2 = stringurl.split("id=", 1)[1]
id = stringurl2.split("id=", 1)[1]
jsstring = "window.parent.openPage('SendSMS?id=" + id + "', 'aSendSMS', 'aSMS', 'ulSMS')"
br.execute_script(jsstring)
time.sleep(8)
br.execute_script(jsstring)
print "JS Executed"
time.sleep(8)
with br.get_iframe('by2Frame') as iframe:
iframe.fill(
"sendSMSMsg",
"Well, I guess robot's do send SMSes when spandan wants them to ;)")
iframe.find_by_tag("input")[10].fill(
"THE_PHONE_NUMBER_YOU_WANT_TO_SEND_SMS_TO")
button2 = iframe.find_by_id("btnsendsms").first
print button2.value
button2.click()
def huoche():
global b
b = Browser(driver_name="chrome")
b.visit(ticket_url)
while b.is_text_present(u"登录"):
sleep(1)
login()
if b.url == initmy_url:
break
try:
print (u"购票页面")
# 跳回购票页面
b.visit(ticket_url)
# 加载查询信息
b.cookies.add({"_jc_save_fromStation": starts})
b.cookies.add({"_jc_save_toStation": ends})
b.cookies.add({"_jc_save_fromDate": dtime})
b.reload()
b.find_by_text(u"更多选项").click()
sleep(1)
b.find_by_id("inp-train").fill(tnum)
b.find_by_id("add-train").click()
#b.find_by_text(u"K-快速").click()
b.find_by_text(u"请选择")[1].click()
b.find_by_text(seatcn)[1].click()
b.execute_script("$.closeSelectSeat()")
sleep(2)
count = 0
flag = ""
# 循环点击预订
print ("order is %s" % order)
if order != 0:
while b.url == ticket_url:
b.find_by_text(u"查询").click()
count +=1
print (u"循环点击查询... 第 %s 次" % count)
sleep(5)
try:
b.find_by_text(u"预订")[order - 1].click()
except:
print (u"还没开始预订")
continue
else:
while b.url == ticket_url:
b.find_by_text(u"查询").click()
count += 1
#flag = b.find_by_id("YW_240000K11711")[0].text
#print ("ticket count is %s" % flag)
sleep(2)
#b.execute_script("$('a:contains("+tnum+")').closest('tr').children('td:eq("+seat+")').addClass('abcde')")
#flag = b.find_by_xpath("//td[@class='abcde']").text
flag = b.find_by_xpath("//td[contains(@id,'"+seat+"')][contains(@id,'"+tnum+"')]").text
print (u"循环点击查询... 第 %s 次 tickets count is %s" % (count,flag))
try:
#for i in b.find_by_text(u"预订"):
# i.click()
if flag != "--" and flag != u"无":
b.execute_script("$('a:contains("+tnum+")').closest('tr').children('td:last').children().click()")
break
except:
print (u"还没开始预订")
continue
sleep(3)
pat = pa.split(",")
while True:
try:
flag = True
for p in pat:
if p == usernamecn:
if b.find_by_text(p)[1].checked != True:
flag = False
b.find_by_text(p)[1].check()
flag = True
else:
if b.find_by_text(p)[0].checked != True:
flag = False
b.find_by_text(p)[0].check()
flag = True
print (u"选择乘客：%s" % p)
if flag:
break
except:
print (u"努力选中陛下的乘客信息中~~~")
sleep(0.5)
print ( u"能做的都做了.....不再对浏览器进行任何操作")
except Exception as e:
print(traceback.print_exc())
