KeyboardInterrupt close failed in file object destructor: sys.excepthook is missing lost sys.stderr
Code
#
#!/usr/bin/env python
import sys, re
def find_position(line):
pun = ""
if re.search(r"[.?!]+", line):
pun = re.search(r"[.?!]+", line).group()
pos = line.find(pun)
pos = pos+len(pun)-1
return pos
def sentence_splitter(filename):
f = open(filename, "r")
for line in f:
line = line.strip()
print line + "\n"
while line:
pos = find_position(line)
line2 = line[ : pos+1].split(" ")
length = len(line2)
last_word = line2[length -1]
try:
if re.search(r"[A-Z]+.*", last_word) or line[pos+1] != " " or
line[pos+2].islower() :
print line[:pos+1],
line = line[pos+1:]
else:
print line[ : pos+1]
line = line[pos+1 :]
except :
print " error here!!"
f.close()
return " bye bye"
if __name__=="__main__":
print sentence_splitter(sys.argv[1])
##3
exicution
python sentence_splitter6.py README | more
###
README
Mr. Smith bought example.cheapsite.com for 1.5 million dollars, i.e. he paid a
lot for it. Did he mind? Adam Jones Jr. thinks he didn't. In any case, this
isn't true... Well, with a probability of .9 it isn't. The result should be:
~
output
Mr. Smith bought example.cheapsite.com for 1.5 million dollars, i.e. he paid a
lot for it. Did he mind? Adam Jones Jr. thinks he didn't.
In any case, this isn't true... Well, with a probability of .9 it isn't. The
result should be:
Mr. Smith bought example. cheapsite. com for 1. 5 million dollars, i. e. he
paid a lot for it.
Did he mind?
Adam Jones Jr. thinks he didn't.
In any case, this isn't true...
Well, with a probability of . 9 it isn't.
##3
error
KeyboardInterrupt
close failed in file object destructor:
sys.excepthook is missing
lost sys.stderr
##
please help what is this i have try lot but unable to remove it
--
https://mail.python.org/mailman/listinfo/python-list
ProgrammingError: (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near 'S SIZE 11.5 NEW IN BOX', '$49.99')' at
from BeautifulSoup import BeautifulSoup
import re, urllib2, MySQLdb
#MySQLdb.escape_string(" ")
import sys
import unicodedata
if __name__=="__main__":
#link = raw_input("Enter the url link: ")
db = MySQLdb.connect("localhost","root","", "ebay")
cursor=db.cursor()
link =
"http://www.ebay.com/sch/Mens-Shoes-/93427/i.html?_pppn=r1&_dcat=93427&LH_ItemCondition=1000%7C1500";
link1 =db.escape_string(link)
page = urllib2.urlopen(link)
soup = BeautifulSoup(page)
Contents = soup.findAll(itemprop = "name")
lst_content = []
for x in Contents:
x = x.string
lst_content.append(x)
Price = soup.findAll(itemprop = "price")
lst_price =[]
for y in Price:
y = y.string
lst_price.append(y)
for x , y in zip(lst_content, lst_price):
sql = """insert into `category` (url, catagory,price) VAlUES ('%s',
'%s', '%s')"""%(link1,x,y)
#print sql
sql = unicodedata.normalize('NFKD', sql).encode('ascii','ignore')
#sys.exit(0)
cursor.execute(sql)
db.commit()
db.close()
+++
error occur
ProgrammingError: (1064, "You have an error in your SQL syntax; check the
manual that corresponds to your MySQL server version for the right syntax to
use near 'S SIZE 11.5 NEW IN BOX', '$49.99')' at line 1")
>>>
--
https://mail.python.org/mailman/listinfo/python-list
please guide to make proxy type function in python
please guide to make proxy type function in python -- https://mail.python.org/mailman/listinfo/python-list
want to run proxy in python
hey , will u guide me how to run proxies from python i have tested lots of code but my ip show always constant on when i see it online plz help . -- https://mail.python.org/mailman/listinfo/python-list
TypeError: not all arguments converted during string formatting
my code :
#!/usr/bin/env python
from bs4 import BeautifulSoup
import re,urllib2,urlparse, MySQLdb
def get_domain(url):
return urlparse.urlparse(url).netloc
def men_tshirts2(main_link, cat_link,db,cursor):
#print main_link
for cat,link in cat_link.iteritems():
cat = str(cat)
#print cat, link
page = urllib2.urlopen(link)
soup = BeautifulSoup(page)
page.close()
item = soup.find_all("div",attrs={"class":"itemTitle"})
price = soup.find_all("div", attrs={"class":"itemPrice"})
item_list =[]
price_list =[]
seller_list =[]
for x,y in zip(item,price):
item_content=str(x.a.string)
price = str(y.p.string)
link = str(x.a.get("href"))
page =urllib2.urlopen(link)
soup = BeautifulSoup(page)
page.close()
data = soup.find_all("span", attrs={"class":"mbg-nw"})
seller = str(data[0].string)
#print cat,item_content,price,seller
gender = "men"
sql = """insert into
fashion(GENDER,links,category,item_content,price,seller)
VAlUES('%s','%s','%s','%s','%s','s')"""
cursor.execute(sql,(gender,main_link,cat,item_content,price,seller))
db.commit()
#except:
#db.rollback()
#print
len(gender),len(main_link),len(cat),len(item_content),len(price),len(seller)
def men_tshirts(db,cursor):
main_link = "http://fashion.ebay.in/index.html#men_tshirts";
domane = get_domain(main_link)
main_page = urllib2.urlopen(main_link)
main_soup=BeautifulSoup(main_page)
main_page.close()
data = main_soup.find_all("div",attrs= {"class":"itmTitle"})
price = main_soup.find_all("span",attrs={"class":"catlblTitle"})
cat_link = {}
for x, y in zip(data, price):
#cat= str(x.a.string)+":"+str(y.string)
cat= str(x.a.string)
link= "http://"+domane+"/"+str(x.a.get("href"))
#print cat, link
cat_link[cat] = link
men_tshirts2(main_link, cat_link,db,cursor)
if __name__=="__main__":
db = MySQLdb.connect("localhost","root","india123","ebay_db" )
cursor = db.cursor()
men_tshirts(db,cursor)
db.close()
++
sql structure :-
mysql> describe fashion;
+--+--+--+-+---++
| Field| Type | Null | Key | Default | Extra
|
+--+--+--+-+---++
| id | int(11) | NO | PRI | NULL | auto_increment
|
| GENDER | varchar(6) | YES | | NULL |
|
| links| varchar(255) | YES | | NULL |
|
| category | varchar(255) | YES | | NULL |
|
| item_content | varchar(255) | YES | | NULL |
|
| price| varchar(10) | YES | | NULL |
|
| seller | varchar(20) | YES | | NULL |
|
| created_on | timestamp| NO | | CURRENT_TIMESTAMP |
|
+--+--+--+-+---++
8 rows in set (0.00 sec)
+++
error:
query = query % db.literal(args)
TypeError: not all arguments converted during string formatting
--
https://mail.python.org/mailman/listinfo/python-list
GUI:-please answer want to learn GUI programming in python , how should i proceed.
GUI:-want to learn GUI programming in python , how should i proceed. There are lots of book here so I am confuse which book i should refer so that i don't waste time . please answer -- https://mail.python.org/mailman/listinfo/python-list
Re: GUI:-please answer want to learn GUI programming in python , how should i proceed.
thank you sir -- https://mail.python.org/mailman/listinfo/python-list
Want guidance to set proxy please help
hey i am working on parsing like project .
so , i need some step to set proxy
so that my ip is not blocked by them
+=
i am using this method
proxy_support = urllib2.ProxyHandler({"http":"http://61.147.82.87:8000"})
opener = urllib2.build_opener(proxy_support)
urllib2.install_opener(opener)
is it ok ? if yes
how can i verify that my i have set proxy
if no, please give some guidance
also if some modification need please help
--
https://mail.python.org/mailman/listinfo/python-list
CAPTCHA HANDLING IN MECHANIZE
HEY , I AM NEW TO THE PYTHON STARTED WORKING ON MECHANIZE , WANT HELP THAT TO HOW TO FILL A FORM HAVING CAPTCHA FIELD AUTOMATIC PLEASE ANSWER -- https://mail.python.org/mailman/listinfo/python-list
HOW TO HANDLE CAPTCHA WHILE PARSING A WEB SITE
RIGHT NOW NOW I AM WORKING WITH MECHANIZE MODULE . BUT UNABLE TO SUBMIT CAPTACHA AUTOMATICALLY . DO U HAVE ANY IDEA PLEASE SHARE WITH ME , ANY IDEA WILL BE APPRECIATES ON ANY M MODULE. -- https://mail.python.org/mailman/listinfo/python-list
how to handle captcha through machanize module or any module
please do replay how to handle captcha through machanize module -- https://mail.python.org/mailman/listinfo/python-list
Re: how to handle captcha through machanize module or any module
#/usr/bin/env python
import mechanize, re
import cookielib
import cgi
import urllib2
from random import choice
def get_domain(url):
return urlparse.urlparse(url).netloc
if __name__=="__main__":
br = mechanize.Browser()
cj = cookielib.LWPCookieJar()
br.set_proxies({"http": "217.174.155.73:8080"})
br.set_cookiejar(cj)
br.addheaders = [('User-agent', 'Firefox')]
br.set_handle_equiv(True)
br.set_handle_gzip(True)
br.set_handle_redirect(True)
br.set_handle_referer(True)
br.set_handle_robots(False)
br.set_handle_refresh(False) # can sometimes hang without this
url = "http://goarticles.com/";
response = br.open(url)
print response.info()
link_list = []
for link in br.links():
match = re.search(r"register", str(link.url))
if match:
link2 = (link.base_url[:-1]+link.url)
if link2 not in link_list:
link_list.append(link2)
print link2
response2 = br.open(link2)
for form in br.forms():
form.set_all_readonly(False)
br.form = list(br.forms())[1] # use when form is unnamed
for control in br.form.controls:
if str(control.type) == "text" and str(control.name) =="email":
br.form[str(control.name)]="jaiprak...@wisepromo.com"
elif str(control.type)=="text":
br.form[str(control.name)]="mybot"+control.name
elif str(control.type) =="select":
br.form[str(control.name)]=[str(control.items[1])]
elif str(control.type) =="password":
br.form[str(control.name)] = "mybotpassword213"
elif str(control.type)=="checkbox":
br.find_control(str(control.name)).items[0].selected=True
elif re.search(r"captcha",str(control.name)):
br.form[str(control.name)] = "mybotcaptcha"
else:
pass
#elif str(control.type)=="submit":
responce = br.submit()
print responce.info()
#print responce.read()
sir , i am very new to python i have just started to learn it ,
my aim is to practice
1)simple automatic form registration,
2)simple automatic vitrification
3)simple automatic loging
this site http://goarticles.com/register.html
sir i m referring the mechanize module
now i am stuck on two thing
1) how to automatically handling the captcha on this form
2) how to verify or the filled form
please help i have already gave 2 days on this just i want some clue from ur
side
--
https://mail.python.org/mailman/listinfo/python-list
Re: HOW TO HANDLE CAPTCHA WHILE PARSING A WEB SITE
sorry sir, it will not happen again in future. -- https://mail.python.org/mailman/listinfo/python-list
Re: HOW TO HANDLE CAPTCHA WHILE PARSING A WEB SITE
sorry sir , it will not happen in future -- https://mail.python.org/mailman/listinfo/python-list
Re: CAPTCHA HANDLING IN MECHANIZE
it will not happen in future -- https://mail.python.org/mailman/listinfo/python-list
python querry on firebug extention
hello
i am working on selenium module of python, i know how to make extension
of firebug with selenium, but i want to know how to use firebug extension
with request module / mechanize . i search a lot but unable to find it , please
help .
technique similar like :-
from selenium import webdriver
fp = webdriver.FirefoxProfile()
fp.add_extension(extension='firebug-1.8.4.xpi')
fp.set_preference("extensions.firebug.currentVersion", "1.8.4") #Avoid startup
screen
browser = webdriver.Firefox(firefox_profile=fp)
--
https://mail.python.org/mailman/listinfo/python-list
Re: How to install googleapp engine on ubuntu 12.04 already downloads google_appengine_1.8.2.zip
got answer downloaded google_appengine_1.8.2.zip unziped it command path-to-/dev_appserver.py path-to/application-diectory that it -- http://mail.python.org/mailman/listinfo/python-list
requesting you all to please guide me , which tutorials is best to learn redis database
hello all, i want to learn redis database and its use via python , please guide me which tutorials i should be study, so that i can learn it in good way I search this on google but i am little confuse, so please help me thank you jai -- https://mail.python.org/mailman/listinfo/python-list
Problem with PEXPECT in Python
import sys,os
import pexpect
source_file= 'sourcefile.txt'
user='username'
ip='00.00.00.00'
desti_path='/home/jai/………'
password='bond007'
cmd ='scp'+' '+source_file+' '+user+'@'+ip+':'+desti_path
try:
foo = pexpect.spawn(cmd)
foo.expect('.ssword:*')
foo.sendline(passwd)
foo.sendline('Passwd_to_server')
foo.interact()
except Exception,e:
pass
Its simple, this should work, it works for me
--
http://mail.python.org/mailman/listinfo/python-list
python query on firebug extention
hello
i am working on selenium module of python, i know how to make
extension of firebug with selenium, but i want to know how to use
firebug extension with request module / mechanize . i search a lot
but unable to find it , please help .
i want technique similar like :-
from selenium import webdriver
fp = webdriver.FirefoxProfile()
fp.add_extension(extension='firebug-.8.4.xpi')
fp.set_preference("extensions.firebug.currentVersion", "1.8.4")
browser = webdriver.Firefox(firefox_profile=fp)
in request module or mechanize module
--
https://mail.python.org/mailman/listinfo/python-list
