def combineTXT(folder,des='combine.txt'):
folder=folderPath(folder)
des=sysPath(des)
g=codecs.open(des,'w','gb18030')
for root, dirs, files in os.walk(folder):
for f in files:
if f.endswith('.txt'):
add=sysPath(root+'/'+f)
fi=codecs.open(add,'r','gb18030')
g.write(fi.read())
g.close()
def combineTXT(folder, des='combine.txt'):
folder = folderPath(folder)
des = sysPath(des)
g = codecs.open(des, 'w', 'gb18030')
for root, dirs, files in os.walk(folder):
for f in files:
if f.endswith('.txt'):
add = sysPath(root + '/' + f)
fi = codecs.open(add, 'r', 'gb18030')
g.write(fi.read())
g.close()
def genTable(filename='../../testData/testingMonuments.txt',\
outfname='../../testData/testingMonumentsData_week4_all.csv', \
months=None,yearBegin=2009, yearEnd=2015,silent=True,endLine=None,\
testNow=False, country='en'):
now = datetime.datetime.now()
now=(int(now.year),int(now.month))
if months==None:
months=[]
for year in range(yearBegin,yearEnd):
for month in range(1,13):
if (year, month)>=now: break
months.append(str(year)+'0'*(2-len(str(month)))+str(month))
months=map(str,months)
filename=sysPath(filename)
f=open(filename,'r')
links=f.read().splitlines()
f.close()
#soup=BeautifulSoup(links)
titleLine=['linkTitle']
for month in months:
titleLine.append('Img'+month)
titleLine.append('Content'+month)
titleLine.append('Traffic'+month)
if not os.path.exists(outfname):
outf=open(outfname,'w')
outf.write('\t'.join(titleLine)+'\n')
start=0
outf.close()
else:
outf=open(outfname,'r')
start=len(outf.read().splitlines())
outf.close()
count=0
## for field in soup.findAll('a')[:endLine]:
for linkTitle in links:
index=linkTitle.find('/wiki/')
if index!=-1:
linkTitle=linkTitle[index+6:]
count+=1
if count<start: continue
## if not field.has_key('title'): continue
## linkTitle=field['href'][6:]
## officialTitle=field['title']
curLine=[linkTitle]
for month in months:
date=month+'01'
revId=getRevId(linkTitle, date+'000000' , silent=silent,country=country) # 6 zeros for h,m,s
if not silent: print 'revId=',revId
if revId==None:
curLine+=['','','']
continue
link='http://'+country+'.wikipedia.org/w/index.php?oldid='+revId
if testNow: print 'title=',linkTitle, 'link=',link,'month=',month
if not silent: print 'prepare'
page=getWebpage(link, timeSleep=0.5,silent=silent)
if not silent: print 'got page'
soup=BeautifulSoup(page)
if not silent: print 'got soup'
numImg=numImage(soup)
if not silent: print 'got num'
conLen=contentLen(soup)
if not silent: print 'got len'
traffic=str(getTraffic(linkTitle,month, silent=silent, country=country))
if not silent: print 'got history'
curLine+=[numImg, conLen, traffic]
curLine=map(str, curLine)
outf=open(outfname,'a')
outf.write('\t'.join(curLine)+'\n')
outf.close()
'''
this program needs to add wait time, may cause problem with your renren id
'''
from getWebpage import getWebpage
import re
import json,time
from sysPath import createFile,sysPath
try:
from BeautifulSoup import BeautifulSoup,SoupStrainer
except:
from bs4 import BeautifulSoup,SoupStrainer # beta version of bs
coo='datr=1HSWUNG14Cr81JphyUZWTl2i; lu=gAff9sJJ2_wuev5W3zxFsGZA; sub=128; p=49; c_user=1216615221; csm=2; fr=0regP7HiBNucJQa1n.AWVfvGNhos7mlakT0e52olU2aWo.BQlnT_.nT.AWVtovRV; s=Aa7LrP8dIAOi4SoX; xs=3%3ArXa_AglvHBTByg%3A2%3A1352037631; act=1356128659553%2F6%3A2; presence=EM356128936EuserFA21216615221A2EstateFDsb2F0Et2F_5b_5dElm2FnullEuct2F135610056B0EtrFA2loadA2EtwF1698182903EatF1356128697024G356128936322CEchFDp_5f1216615221F8CC; wd=1280x299'
f=open(sysPath('webpages/ids.txt'))
jf=json.loads(f.read().decode('utf8','ignore'))
f.close()
createFile('infos_fb.txt',force=True)
g=open('infos_fb.txt','a')
g.write('Name,Given Name,Additional Name,Family Name,Yomi Name,Given Name Yomi,Additional Name Yomi,Family Name Yomi,Name Prefix,Name Suffix,Initials,Nickname,Short Name,Maiden Name,Birthday,Gender,Location,Billing Information,Directory Server,Mileage,Occupation,Hobby,Sensitivity,Priority,Subject,Notes,Group Membership,E-mail 1 - Type,E-mail 1 - Value,E-mail 2 - Type,E-mail 2 - Value,Phone 1 - Type,Phone 1 - Value'+'\n')
g.close()
ans=[]
for f in jf['data']:
info=getWebpage('http://www.facebook.com/'+str(f['id']),
cookies=coo,
info=str(f['id'])
)
bI=BeautifulSoup(info)
link=bI.find('link',{'rel':'alternate'})
'''
'''
this program needs to add wait time, may cause problem with your renren id
'''
from getWebpage import getWebpage
import re
import json, time
from sysPath import createFile, sysPath
try:
from BeautifulSoup import BeautifulSoup, SoupStrainer
except:
from bs4 import BeautifulSoup, SoupStrainer # beta version of bs
coo = 'datr=1HSWUNG14Cr81JphyUZWTl2i; lu=gAff9sJJ2_wuev5W3zxFsGZA; sub=128; p=49; c_user=1216615221; csm=2; fr=0regP7HiBNucJQa1n.AWVfvGNhos7mlakT0e52olU2aWo.BQlnT_.nT.AWVtovRV; s=Aa7LrP8dIAOi4SoX; xs=3%3ArXa_AglvHBTByg%3A2%3A1352037631; act=1356128659553%2F6%3A2; presence=EM356128936EuserFA21216615221A2EstateFDsb2F0Et2F_5b_5dElm2FnullEuct2F135610056B0EtrFA2loadA2EtwF1698182903EatF1356128697024G356128936322CEchFDp_5f1216615221F8CC; wd=1280x299'
f = open(sysPath('webpages/ids.txt'))
jf = json.loads(f.read().decode('utf8', 'ignore'))
f.close()
createFile('infos_fb.txt', force=True)
g = open('infos_fb.txt', 'a')
g.write(
'Name,Given Name,Additional Name,Family Name,Yomi Name,Given Name Yomi,Additional Name Yomi,Family Name Yomi,Name Prefix,Name Suffix,Initials,Nickname,Short Name,Maiden Name,Birthday,Gender,Location,Billing Information,Directory Server,Mileage,Occupation,Hobby,Sensitivity,Priority,Subject,Notes,Group Membership,E-mail 1 - Type,E-mail 1 - Value,E-mail 2 - Type,E-mail 2 - Value,Phone 1 - Type,Phone 1 - Value'
+ '\n')
g.close()
ans = []
for f in jf['data']:
info = getWebpage('http://www.facebook.com/' + str(f['id']),
cookies=coo,
info=str(f['id']))
bI = BeautifulSoup(info)
link = bI.find('link', {'rel': 'alternate'})
