def doOneTask(self, task):
#0. sign it
self.signTask(task)
task.status = 'parsing'
#1. call handler
if task.handler not in self.hs:
#from MainPageHandler import MainPageHandler
m = __import__(task.handler)
c = getattr(m, task.handler)
self.hs[task.handler] = c()
h = self.hs[task.handler]
#2. check type and do it
isOK = True
if task.taskType in ('media', 'page'):
#deal with it
output = {}
try:
output = h.parse(task)
except Exception, e:
# todo set task failed here
util.printException()
myLogger.error("sth wrong [%s][%s] in parsing, set task[%d] failed" % (task.handler, e, task.id))
isOK = False
if 'newTasks' in output:
for t in output['newTasks']:
# get a taskId from my manager
self.m.packTask(t)
self.signTask(t)
self.m.addTask(t)
def run(self):
myLogger.info("worker %s begin to run" % (self.name))
myLogger.info("my manager's inQueue size [%d]" % (self.inQueue.qsize()))
self.hungerly = False
while True:
try:
# get
get = None
try:
get = self.inQueue.get(timeout=1)
self.hungerly = False
except Queue.Empty, e:
self.hungerly = True
myLogger.debug('thread [%s] is hungerly now' % (self.name))
if self.m.shouldExit == True:
myLogger.debug('thread [%s] is exiting' % (self.name))
break
if self.hungerly == False:
# do
myLogger.info("thread [%s], get task[%s] from queue" % (self.name, get.id))
time.sleep(3)
# put
self.doOneTask(get)
else:
time.sleep(2)
except Exception, e:
util.printException()
myLogger.error('sth wrong[%s] in thread [%s]' % (e, self.name))
get.status = 'failed'
if get.msg != '':
get.msg = util.exprException()
def download(self, url, to, postdata={}, timeout=60, times=3, safeFetch=True):
myLogger.info("fetcher download from [%s] to [%s]" % (url, to))
ret = None
while times!=0:
status=''
if safeFetch == True:
resp = self.safeFetch(url, postdata, timeout)
else:
resp, status = self.fetch(url, postdata, timeout)
if util.mkdir(os.path.dirname(to)) == False:
times -= 1
ret = None
continue
if status == 'OK' or (status == '' and resp != None): # fetch ok
CHUNK = 1024 * 1024 * 5
with open(to, 'wb') as f:
ret = True
try:
while True:
chunk = resp.read(CHUNK)
if not chunk:
break
f.write(chunk)
except Exception, e:
msg = util.exprException()
util.printException()
ret = None
if ret == True:
break
times -= 1
def run(self):
myLogger.info("worker %s begin to run" % (self.name))
myLogger.info("my manager's inQueue size [%d]" %
(self.inQueue.qsize()))
self.hungerly = False
while True:
try:
# get
get = None
try:
get = self.inQueue.get(timeout=1)
self.hungerly = False
except Queue.Empty, e:
self.hungerly = True
myLogger.debug('thread [%s] is hungerly now' % (self.name))
if self.m.shouldExit == True:
myLogger.debug('thread [%s] is exiting' % (self.name))
break
if self.hungerly == False:
# do
myLogger.info("thread [%s], get task[%s] from queue" %
(self.name, get.id))
time.sleep(3)
# put
self.doOneTask(get)
else:
time.sleep(2)
except Exception, e:
util.printException()
myLogger.error('sth wrong[%s] in thread [%s]' % (e, self.name))
get.status = 'failed'
if get.msg != '':
get.msg = util.exprException()
def doOneTask(self, task):
#0. sign it
self.signTask(task)
task.status = 'parsing'
#1. call handler
if task.handler not in self.hs:
#from MainPageHandler import MainPageHandler
m = __import__(task.handler)
c = getattr(m, task.handler)
self.hs[task.handler] = c()
h = self.hs[task.handler]
#2. check type and do it
isOK = True
if task.taskType in ('media', 'page'):
#deal with it
output = {}
try:
output = h.parse(task)
except Exception, e:
# todo set task failed here
util.printException()
myLogger.error(
"sth wrong [%s][%s] in parsing, set task[%d] failed" %
(task.handler, e, task.id))
isOK = False
if 'newTasks' in output:
for t in output['newTasks']:
# get a taskId from my manager
self.m.packTask(t)
self.signTask(t)
self.m.addTask(t)
def parseContent(self, page):
page = page.decode('gbk')
ret = {'stockList': [], 'nextPage': ''}
try:
soup = BS(page)
theA = soup.find('a', text='下一页')
if theA != None and theA['href'] != '':
ret['nextPage'] = theA['href']
table = soup.find('table',
width="100%",
cellspacing="1",
cellpadding="2",
border="0",
bgcolor="#337fb2")
trList = table.find_all('tr')
for tr in trList[1:]:
tdList = tr.find_all('td')
code = tdList[0].text
name = tdList[1].text
href = tdList[0].a['href']
ret['stockList'].append({
'code': code,
'name': name,
'href': href
})
except Exception, e:
util.printException()
return (None, e)
def ensureSIFTFeatures(filepath,
paramsSIFT,
properties,
csvDir,
validateByFileExists=False):
"""
filepath: to the image from which SIFT features have been or have to be extracted.
params: dict of registration parameters, including the key "scale".
paramsSIFT: FloatArray2DSIFT.Params instance.
csvDir: directory into which serialized features have been or will be saved.
load: function to load an image as an ImageProcessor from the filepath.
validateByFileExists: whether to merely check that the .obj file exists as a quick form of validation.
First check if serialized features exist for the image, and if the Params match.
Otherwise extract the features and store them serialized.
Returns the ArrayList of Feature instances.
"""
path = os.path.join(csvDir,
os.path.basename(filepath) + ".SIFT-features.obj")
if validateByFileExists:
if os.path.exists(path):
return True
# An ArrayList whose last element is a mpicbg.imagefeatures.FloatArray2DSIFT.Param
# and all other elements are mpicbg.imagefeatures.Feature
features = deserialize(path) if os.path.exists(path) else None
if features:
if features.get(features.size() - 1).equals(paramsSIFT):
features.remove(features.size() - 1) # removes the Params
syncPrintQ("Loaded %i SIFT features for %s" %
(features.size(), os.path.basename(filepath)))
return features
else:
# Remove the file: paramsSIFT have changed
os.remove(path)
# Else, extract de novo:
try:
# Extract features
imp = loadImp(filepath)
ip = imp.getProcessor()
paramsSIFT = paramsSIFT.clone()
ijSIFT = SIFT(FloatArray2DSIFT(paramsSIFT))
features = ArrayList() # of Feature instances
ijSIFT.extractFeatures(ip, features)
ip = None
imp.flush()
imp = None
features.add(
paramsSIFT
) # append Params instance at the end for future validation
serialize(features, path)
features.remove(features.size() -
1) # to return without the Params for immediate use
syncPrintQ("Extracted %i SIFT features for %s" %
(features.size(), os.path.basename(filepath)))
except:
printException()
return features
def parseContent(self, page):
ret = {'excelUrl':''}
try:
soup = BS(page)
td = soup.find('td', align="right", width="60px", valign="bottom")
print td
print td.a['href']
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = {}
soup = BS(page)
try:
li = soup.find('li', 'downloadlinkstatic')
src = li.a.get('href')
ret['contentMp3'] = src
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = {'excelUrl': ''}
try:
soup = BS(page)
td = soup.find('td', align="right", width="60px", valign="bottom")
print td
print td.a['href']
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = {}
soup = BS(page)
try:
li = soup.find('li', 'downloadlinkstatic')
src = li.a.get('href')
ret['contentMp3'] = src
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = []
page = page.decode('utf-8')
try:
soup = BS(page)
tableDiv = soup.find('div', class_='genTable')
trList = tableDiv.find_all('tr')
for tr in trList:
ret.append(tr.text)
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = []
page = page.decode('utf-8')
try:
soup = BS(page)
tableDiv = soup.find('div', class_='genTable')
trList = tableDiv.find_all('tr')
for tr in trList:
ret.append(tr.text)
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = []
try:
soup = BS(page)
headerDiv = soup.find(id='indexItems')
headlis = headerDiv.select('li')
for li in headlis:
iUrl = urlparse.urljoin(li.a['href'].rstrip(".html")+"/", "pc10.html?tab=None")
#iUrl = urlparse.urljoin(li.a['href'].rstrip(".html")+"/", "pc0.html?tab=None")
ret.append(iUrl)
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = {}
try:
soup = BS(page.decode('gbk'))
table = soup.find('table', width="92%", cellspacing="1", cellpadding="2", border="0")
trList = table.find_all('tr')
for tr in trList:
tdList = tr.find_all('td')
if len(tdList) <= 1:
continue
k = tdList[0].text.strip().split(":")[0]
v = tdList[1].text.strip()
ret[k] = v
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = []
try:
soup = BS(page)
headerDiv = soup.find(id='header')
headlis = headerDiv.select('li.header_navigation_item.has_child')
for li in headlis:
if li.a.text == 'Audio':
links = li.find_all('a', 'section_link')
break
for link in links:
ret.append(link['href'])
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = {'stockInfoPage':{}, 'stockList':[]}
try:
soup = BS(page)
trList = soup.find_all('tr', class_ ='tr_normal' )
for tr in trList:
tdList = tr.find_all('td')
href = ''
if hasattr(tdList[1], 'a') and tdList[1].a != None and tdList[1].a != '':
href = tdList[1].a['href']
textList = [ td.text for td in tdList ]
textList.append(href)
ret['stockList'].append(textList)
ret['stockInfoPage'][textList[0]] = href
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = {"zipPic": {}, "contentPage": {}}
try:
soup = BS(page)
articleUl = soup.find(id="articleItems")
# ul = soup.find('ul', "bullet_orange")
divs = articleUl.find_all("div", "media-block")
for div in divs:
zipPic = div.img.get("src")
# has audio?
a = div.find("a", "img-wrapper")
if a and a["href"] != "":
url = a.get("href")
key = url.replace("/", "_")
ret["zipPic"][key] = zipPic
ret["contentPage"][key] = url
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
page = page.decode('gbk')
ret = {'stockList':[], 'nextPage':''}
try:
soup = BS(page)
theA = soup.find('a', text='下一页')
if theA != None and theA['href'] != '':
ret['nextPage'] = theA['href']
table = soup.find('table', width="100%", cellspacing="1", cellpadding="2", border="0", bgcolor="#337fb2")
trList = table.find_all('tr')
for tr in trList[1:]:
tdList = tr.find_all('td')
code = tdList[0].text
name = tdList[1].text
href = tdList[0].a['href']
ret['stockList'].append({'code': code, 'name': name, 'href': href})
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = {}
try:
soup = BS(page.decode('gbk'))
table = soup.find('table',
width="92%",
cellspacing="1",
cellpadding="2",
border="0")
trList = table.find_all('tr')
for tr in trList:
tdList = tr.find_all('td')
if len(tdList) <= 1:
continue
k = tdList[0].text.strip().split(":")[0]
v = tdList[1].text.strip()
ret[k] = v
except Exception, e:
util.printException()
return (None, e)
def extractSIFTMatches(filepath1, filepath2, params, paramsSIFT, properties,
csvDir):
# Skip if pointmatches CSV file exists already:
csvpath = os.path.join(
csvDir,
basename(filepath1) + '.' + basename(filepath2) + ".pointmatches.csv")
if os.path.exists(csvpath):
return False
try:
# Load from CSV files or extract features de novo
features1 = ensureSIFTFeatures(filepath1, paramsSIFT, properties,
csvDir)
features2 = ensureSIFTFeatures(filepath2, paramsSIFT, properties,
csvDir)
#syncPrintQ("Loaded %i features for %s\n %i features for %s" % (features1.size(), os.path.basename(filepath1),
# features2.size(), os.path.basename(filepath2)))
# Vector of PointMatch instances
sourceMatches = FloatArray2DSIFT.createMatches(
features1,
features2,
params.get(
"max_sd",
1.5), # max_sd: maximal difference in size (ratio max/min)
TranslationModel2D(),
params.get(
"max_id",
Double.MAX_VALUE), # max_id: maximal distance in image space
params.get("rod", 0.9)) # rod: ratio of best vs second best
syncPrintQ("Found %i SIFT pointmatches for %s vs %s" %
(sourceMatches.size(), os.path.basename(filepath1),
os.path.basename(filepath2)))
# Store pointmatches
savePointMatches(os.path.basename(filepath1),
os.path.basename(filepath2), sourceMatches, csvDir,
params)
return True
except:
printException()
def loadFeatures(img_filename,
directory,
params,
validateOnly=False,
epsilon=0.00001,
verbose=True):
""" Attempts to load features from filename + ".features.csv" if it exists,
returning a list of Constellation features or None.
params: dictionary of parameters with which features are wanted now,
to compare with parameter with which features were extracted.
In case of mismatch, return None.
epsilon: allowed error when comparing floating-point values.
validateOnly: if True, return after checking that parameters match. """
try:
csvpath = os.path.join(directory,
basename(img_filename) + ".features.csv")
if os.path.exists(csvpath):
with open(csvpath, 'r') as csvfile:
reader = csv.reader(csvfile, delimiter=',', quotechar='"')
# First line contains parameter names, second line their values
if not checkParams(params, reader.next(), reader.next(),
epsilon):
return None
if validateOnly:
return True # would return None above, which is falsy
reader.next() # skip header with column names
features = [
Constellation.fromRow(map(float, row)) for row in reader
]
if verbose:
syncPrint("Loaded %i features for %s" %
(len(features), img_filename))
return features
else:
if verbose:
syncPrint("No stored features found at %s" % csvpath)
return None
except:
syncPrint("Could not load features for %s" % img_filename)
printException()
return None
def parseContent(self, page):
ret = {'zipPic':{}, 'contentPage':{}}
try:
soup = BS(page)
titleDiv = soup.find(id='archive').h2
classTitle = titleDiv.text
ul = soup.find('ul', "bullet_orange")
divs = ul.find_all('div', 'archive_rowmm')
for div in divs:
zipPic = div.img.get('src')
#has audio?
a = div.h4.a
if a.select('span.assignedIcon.asIcoAudio') != []:
span = a.find('span', 'underlineLink')
url = a.get('href')
key = url.replace('/', '_')
ret['zipPic'][key] = zipPic
ret['contentPage'][key] = url
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = {'zipPic': {}, 'contentPage': {}}
try:
soup = BS(page)
titleDiv = soup.find(id='archive').h2
classTitle = titleDiv.text
ul = soup.find('ul', "bullet_orange")
divs = ul.find_all('div', 'archive_rowmm')
for div in divs:
zipPic = div.img.get('src')
#has audio?
a = div.h4.a
if a.select('span.assignedIcon.asIcoAudio') != []:
span = a.find('span', 'underlineLink')
url = a.get('href')
key = url.replace('/', '_')
ret['zipPic'][key] = zipPic
ret['contentPage'][key] = url
except Exception, e:
util.printException()
return (None, e)
def loadPointMatches(img1_filename,
img2_filename,
directory,
params,
epsilon=0.00001,
verbose=True):
""" Attempts to load point matches from filename1 + '.' + filename2 + ".pointmatches.csv" if it exists,
returning a list of PointMatch instances or None.
params: dictionary of parameters with which pointmatches are wanted now,
to compare with parameter with which pointmatches were made.
In case of mismatch, return None.
epsilon: allowed error when comparing floating-point values. """
try:
csvpath = os.path.join(
directory,
basename(img1_filename) + '.' + basename(img2_filename) +
".pointmatches.csv")
if not os.path.exists(csvpath):
if verbose:
syncPrint("No stored pointmatches found at %s" % csvpath)
return None
with open(csvpath, 'r') as csvfile:
reader = csv.reader(csvfile, delimiter=',', quotechar='"')
# First line contains parameter names, second line their values
if not checkParams(params, reader.next(), reader.next(), epsilon):
return None
if next(reader, None) is None: # skip header with column names
return [] # zero pointmatches
pointmatches = PointMatches.fromRows(reader).pointmatches
if verbose:
syncPrint("Loaded %i pointmatches for %s, %s" %
(len(pointmatches), img1_filename, img2_filename))
return pointmatches
except:
syncPrint("Could not load pointmatches for pair %s, %s" %
(img1_filename, img2_filename))
printException()
return None
def parseContent(self, page):
ret = {'contentPics':[], 'contentPicCaptions':[], 'embPics':[]}
try:
soup = BS(page)
articleDiv = soup.find('div', id='article')
siteTitleH2 = articleDiv.find('h2', 'sitetitle')
ret['siteTitle'] = siteTitleH2.a.text
titleH1 = articleDiv.find('h1')
ret['title'] = titleH1.text.strip()
picDiv = soup.find('div', 'watermark')
if picDiv and picDiv.parent['class'] == ['contentImage', 'floatNone']:
ret['contentPics'].append(picDiv.a.img.get('src'))
ret['contentPicCaptions'].append(picDiv.next_sibling.text)
li = soup.find('li', 'downloadlinkstatic')
if li != None:
src = li.a.get('href')
ret['contentMp3'] = src
else:
li = soup.find('li', 'listenlink')
url = li.a.get('href')
ret['contentMp3Page'] = url
contentDiv = articleDiv.find('div', 'articleContent')
dateDiv = contentDiv.find('div', 'dateblock')
date = dateDiv.text.strip()
ret['date'] = date
contentZoomMeDiv = contentDiv.find('div', 'zoomMe')
#delete mp3 player part
mp3H5 = contentZoomMeDiv.find('h5', 'tagaudiotitle')
if mp3H5:
print mp3H5
div = mp3H5.find_next_sibling('div', 'mediaplayer audioplayer')
div.decompose()
mp3H5.decompose()
#delete script
for ele in contentZoomMeDiv.find_all('script'):
ele.decompose()
for ul in contentZoomMeDiv.find_all('ul'):
if ul.find('li', 'playlistlink') or \
ul.find('li', 'listenlink'):
ul.decompose()
#print contentZoomMeDiv
#delete until first p
if contentZoomMeDiv.find('div', 'wordclick'):
iterContent = contentZoomMeDiv.find('div', 'wordclick')
else:
iterContent = contentZoomMeDiv
for tag in iterContent.find_all():
if tag.name != None:
if tag.name != 'p' and tag.name != 'br':
tag.decompose()
else:
break
keepDelete = False
for tag in iterContent.find_all():
if tag.name != None:
if keepDelete == False:
if tag.name == 'div':
tagClass = tag.get('class')
if tag.find('p') and self.reXHX.search(tag.p.text):
oriTag = tag
tag = tag.p
if tag.find_next_sibling('h5', 'tagaudiotitle') or \
tag.find_next_sibling('div', ['mediaplayer', 'audioplayer']):
keepDelete = True
tag.decompose()
#if tag.find('span') and self.reXHX.search(tag.span.text):
# print tag
# #keepDelete = True
# #tag.span.decompose()
#elif tag.find('em') and self.reXHX.search(tag.em.text):
# print tag
# #keepDelete = True
# #tag.em.decompose()
#elif self.reXHX.search(tag.text):
# print tag
# #keepDelete = True
# #tag.decompose()
elif tagClass:
if 'infgraphicsAttach' in tagClass:
tag.decompose()
if 'boxwidget' in tagClass:
#boxwidget w_Quiz2c w_QuizInside
tag.decompose()
elif tag.name == 'iframe':
tag.decompose()
elif tag.name == 'p':
#check em
if tag.find('span') and self.reXHX.search(tag.span.text):
#print tag
#keepDelete = True
#tag.span.decompose()
if tag.find_next_sibling('h5', 'tagaudiotitle') or \
tag.find_next_sibling('div', ['mediaplayer', 'audioplayer']):
keepDelete = True
tag.decompose()
elif tag.find('em') and self.reXHX.search(tag.em.text):
#print tag
#keepDelete = True
#tag.em.decompose()
if tag.find_next_sibling('h5', 'tagaudiotitle') or \
tag.find_next_sibling('div', ['mediaplayer', 'audioplayer']):
keepDelete = True
tag.decompose()
elif self.reXHX.search(tag.text):
print tag
#keepDelete = True
#tag.decompose()
if tag.find_next_sibling('h5', 'tagaudiotitle') or \
tag.find_next_sibling('div', ['mediaplayer', 'audioplayer']):
keepDelete = True
tag.decompose()
else:
tag.decompose()
#print contentZoomMeDiv
#filt photos in content
for tag in iterContent.find_all():
if tag.name == 'div' and tag.get('class'):
if 'embedded_content_object' in tag.get('class'):
embDiv = tag
embImgDiv = embDiv.find('div', 'contentImage')
if embImgDiv:
embImg = embImgDiv.find('img')
src = embImg.get('src')
ret['embPics'].append(src)
newSrc = os.path.basename(urlparse.urlparse(src).path)
embImg['src'] = newSrc
tag.replace_with(embImgDiv)
else:
tag.decompose()
ret['content'] = "%s" % contentZoomMeDiv.prettify().encode('utf-8')
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
ret = {'contentPics': [], 'contentPicCaptions': [], 'embPics': []}
try:
soup = BS(page)
articleDiv = soup.find('div', id='article')
siteTitleH2 = articleDiv.find('h2', 'sitetitle')
ret['siteTitle'] = siteTitleH2.a.text
titleH1 = articleDiv.find('h1')
ret['title'] = titleH1.text.strip()
picDiv = soup.find('div', 'watermark')
if picDiv and picDiv.parent['class'] == [
'contentImage', 'floatNone'
]:
ret['contentPics'].append(picDiv.a.img.get('src'))
ret['contentPicCaptions'].append(picDiv.next_sibling.text)
li = soup.find('li', 'downloadlinkstatic')
if li != None:
src = li.a.get('href')
ret['contentMp3'] = src
else:
li = soup.find('li', 'listenlink')
url = li.a.get('href')
ret['contentMp3Page'] = url
contentDiv = articleDiv.find('div', 'articleContent')
dateDiv = contentDiv.find('div', 'dateblock')
date = dateDiv.text.strip()
ret['date'] = date
contentZoomMeDiv = contentDiv.find('div', 'zoomMe')
#delete mp3 player part
mp3H5 = contentZoomMeDiv.find('h5', 'tagaudiotitle')
if mp3H5:
print mp3H5
div = mp3H5.find_next_sibling('div', 'mediaplayer audioplayer')
div.decompose()
mp3H5.decompose()
#delete script
for ele in contentZoomMeDiv.find_all('script'):
ele.decompose()
for ul in contentZoomMeDiv.find_all('ul'):
if ul.find('li', 'playlistlink') or \
ul.find('li', 'listenlink'):
ul.decompose()
#print contentZoomMeDiv
#delete until first p
if contentZoomMeDiv.find('div', 'wordclick'):
iterContent = contentZoomMeDiv.find('div', 'wordclick')
else:
iterContent = contentZoomMeDiv
for tag in iterContent.find_all():
if tag.name != None:
if tag.name != 'p' and tag.name != 'br':
tag.decompose()
else:
break
keepDelete = False
for tag in iterContent.find_all():
if tag.name != None:
if keepDelete == False:
if tag.name == 'div':
tagClass = tag.get('class')
if tag.find('p') and self.reXHX.search(tag.p.text):
oriTag = tag
tag = tag.p
if tag.find_next_sibling('h5', 'tagaudiotitle') or \
tag.find_next_sibling('div', ['mediaplayer', 'audioplayer']):
keepDelete = True
tag.decompose()
#if tag.find('span') and self.reXHX.search(tag.span.text):
# print tag
# #keepDelete = True
# #tag.span.decompose()
#elif tag.find('em') and self.reXHX.search(tag.em.text):
# print tag
# #keepDelete = True
# #tag.em.decompose()
#elif self.reXHX.search(tag.text):
# print tag
# #keepDelete = True
# #tag.decompose()
elif tagClass:
if 'infgraphicsAttach' in tagClass:
tag.decompose()
if 'boxwidget' in tagClass:
#boxwidget w_Quiz2c w_QuizInside
tag.decompose()
elif tag.name == 'iframe':
tag.decompose()
elif tag.name == 'p':
#check em
if tag.find('span') and self.reXHX.search(
tag.span.text):
#print tag
#keepDelete = True
#tag.span.decompose()
if tag.find_next_sibling('h5', 'tagaudiotitle') or \
tag.find_next_sibling('div', ['mediaplayer', 'audioplayer']):
keepDelete = True
tag.decompose()
elif tag.find('em') and self.reXHX.search(
tag.em.text):
#print tag
#keepDelete = True
#tag.em.decompose()
if tag.find_next_sibling('h5', 'tagaudiotitle') or \
tag.find_next_sibling('div', ['mediaplayer', 'audioplayer']):
keepDelete = True
tag.decompose()
elif self.reXHX.search(tag.text):
print tag
#keepDelete = True
#tag.decompose()
if tag.find_next_sibling('h5', 'tagaudiotitle') or \
tag.find_next_sibling('div', ['mediaplayer', 'audioplayer']):
keepDelete = True
tag.decompose()
else:
tag.decompose()
#print contentZoomMeDiv
#filt photos in content
for tag in iterContent.find_all():
if tag.name == 'div' and tag.get('class'):
if 'embedded_content_object' in tag.get('class'):
embDiv = tag
embImgDiv = embDiv.find('div', 'contentImage')
if embImgDiv:
embImg = embImgDiv.find('img')
src = embImg.get('src')
ret['embPics'].append(src)
newSrc = os.path.basename(
urlparse.urlparse(src).path)
embImg['src'] = newSrc
tag.replace_with(embImgDiv)
else:
tag.decompose()
ret['content'] = "%s" % contentZoomMeDiv.prettify().encode('utf-8')
except Exception, e:
util.printException()
return (None, e)
def parseContent(self, page):
page = page.decode('gbk')
ret = {'stockBasicInfo':{}, 'stockOtherInfo':{}}
transMapCn2En = {
u'公司代码': 'compCode',
u'注册地址': 'registerAddr',
u'法定代表人': 'legalRepresentative',
u'董事会秘书姓名': 'boardSecretary',
u'E-mail': 'E-mail',
u'联系电话': 'phone',
u'网址':'website',
u'SSE行业': 'sseSector',
u'是否上证180样本股': 'isSh180',
u'是否境外上市': 'isOverseasListing',
u'境外上市地': 'OverseasListingPlace'
}
try:
soup = BS(page)
titleSpan = soup.find('span', class_ ='pagetitle' )
br = titleSpan.find('br')
cmpNameAndCode = br.previous_element
cmpName, code = re.split("\s+", cmpNameAndCode.strip())
table = soup.find('table', width="100%", cellspacing="5", cellpadding="0", border="0")
contentTd = table.find('td', class_="content", width="100%", valign="top")
#contentTableList = contentTd.find_all('table', class="content", width="100%", bgcolor="#FFFFFF", align="center")
tdList = contentTd.find_all('td', class_="content_b")
for td in tdList:
key = re.sub(r"\s+", "", td.text.strip().strip(':'))
value = td.find_next_sibling('td').text.strip()
if key == u'股票代码(A股/B股)':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['code'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['B_code'] = ''
else:
ret['stockBasicInfo']['B_code'] = valueList[1]
elif key == u'上市日(A股/B股)':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['A_IPO_date'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['B_IPO_date'] = ''
else:
ret['stockBasicInfo']['B_IPO_date'] = valueList[1]
elif key == u'可转债简称（代码）':
valueListMatch = re.search(ur"(\.+)\s*（(.+)）", value)
if valueListMatch != None:
groups = valueListMatch.groups()
ret['stockBasicInfo']['convertibleBondAbbr'] = groups[0]
ret['stockBasicInfo']['convertibleBondCode'] = groups[1]
else:
ret['stockBasicInfo']['convertibleBondAbbr'] = ''
ret['stockBasicInfo']['convertibleBondCode'] = ''
elif key == u'公司简称(中/英)':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['compNameAbbr'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['compNameAbbrEn'] = ''
else:
ret['stockBasicInfo']['compNameAbbrEn'] = valueList[1]
elif key == u'公司全称(中/英)':
valueList = value.split("\n")
ret['stockBasicInfo']['compNameCn'] = valueList[0]
ret['stockBasicInfo']['compNameEn'] = valueList[1]
elif key == u'通讯地址（邮编）':
value = value.replace("\n", "")
valueListMatch = re.search(ur"(\.+)\s*（(.+)）", value)
if valueListMatch != None:
groups = valueListMatch.groups()
ret['stockBasicInfo']['contactAddr'] = groups[0]
ret['stockBasicInfo']['postcode'] = groups[1]
else:
ret['stockBasicInfo']['contactAddr'] = ''
ret['stockBasicInfo']['postcode'] = ''
elif key.startswith(u'CSRC行业'):
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['sector'] = "/".join(valueList)
ret['stockBasicInfo']['sector1'] = valueList[0]
ret['stockBasicInfo']['sector2'] = valueList[1]
if valueList[2] == '-':
ret['stockBasicInfo']['sector3'] = valueList[1]
else:
ret['stockBasicInfo']['sector3'] = valueList[2]
elif key == u'所属省/直辖市':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['province'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['city'] = ''
else:
ret['stockBasicInfo']['city'] = valueList[1]
elif key == u'A股状态/B股状态':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['A_status'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['B_status'] = ''
else:
ret['stockBasicInfo']['B_status'] = valueList[1]
else:
if key in transMapCn2En:
ret['stockBasicInfo'][transMapCn2En[key]] = value.strip()
else:
ret['stockBasicInfo'][key] = value.strip()
except Exception, e:
util.printException()
return (None, e)
def extractBlockMatches(filepath1, filepath2, params, paramsSIFT, properties,
csvDir, exeload, load):
"""
filepath1: the file path to an image of a section.
filepath2: the file path to an image of another section.
params: dictionary of parameters necessary for BlockMatching.
exeload: an ExecutorService for parallel loading of image files.
load: a function that knows how to load the image from the filepath.
return False if the CSV file already exists, True if it has to be computed.
"""
# Skip if pointmatches CSV file exists already:
csvpath = os.path.join(
csvDir,
basename(filepath1) + '.' + basename(filepath2) + ".pointmatches.csv")
if os.path.exists(csvpath):
return False
try:
# Load files in parallel
futures = [
exeload.submit(Task(load, filepath1)),
exeload.submit(Task(load, filepath2))
]
fp1 = futures[0].get(
) # FloatProcessor, already Gaussian-blurred, contrast-corrected and scaled!
fp2 = futures[1].get() # FloatProcessor, idem
# Define points from the mesh
sourcePoints = ArrayList()
# List to fill
sourceMatches = ArrayList(
) # of PointMatch from filepath1 to filepath2
# Don't use blockmatching if the dimensions are different
use_blockmatching = fp1.getWidth() == fp2.getWidth() and fp1.getHeight(
) == fp2.getHeight()
# Fill the sourcePoints
mesh = TransformMesh(params["meshResolution"], fp1.width, fp1.height)
PointMatch.sourcePoints(mesh.getVA().keySet(), sourcePoints)
syncPrintQ("Extracting block matches for \n S: " + filepath1 +
"\n T: " + filepath2 + "\n with " +
str(sourcePoints.size()) + " mesh sourcePoints.")
# Run
BlockMatching.matchByMaximalPMCCFromPreScaledImages(
fp1,
fp2,
params["scale"], # float
params["blockRadius"], # X
params["blockRadius"], # Y
params["searchRadius"], # X
params["searchRadius"], # Y
params["minR"], # float
params["rod"], # float
params["maxCurvature"], # float
sourcePoints,
sourceMatches)
# At least some should match to accept the translation
if len(sourceMatches) < max(20, len(sourcePoints) / 5) / 2:
syncPrintQ(
"Found only %i blockmatching pointmatches (from %i source points)"
% (len(sourceMatches), len(sourcePoints)))
syncPrintQ(
"... therefore invoking SIFT pointmatching for:\n S: " +
basename(filepath1) + "\n T: " + basename(filepath2))
# Can fail if there is a shift larger than the searchRadius
# Try SIFT features, which are location independent
#
# Images are now scaled: load originals
futures = [
exeload.submit(
Task(loadFloatProcessor,
filepath1,
params,
paramsSIFT,
scale=False)),
exeload.submit(
Task(loadFloatProcessor,
filepath2,
params,
paramsSIFT,
scale=False))
]
fp1 = futures[0].get() # FloatProcessor, original
fp2 = futures[1].get() # FloatProcessor, original
# Images can be of different size: scale them the same way
area1 = fp1.width * fp1.height
area2 = fp2.width * fp2.height
if area1 == area2:
paramsSIFT1 = paramsSIFT.clone()
paramsSIFT1.maxOctaveSize = int(
max(properties.get("SIFT_max_size", 2048),
fp1.width * params["scale"]))
paramsSIFT1.minOctaveSize = int(paramsSIFT1.maxOctaveSize /
pow(2, paramsSIFT1.steps))
paramsSIFT2 = paramsSIFT1
else:
bigger, smaller = (fp1, fp2) if area1 > area2 else (fp2, fp1)
target_width_bigger = int(
max(1024, bigger.width * params["scale"]))
if 1024 == target_width_bigger:
target_width_smaller = int(1024 * float(smaller.width) /
bigger.width)
else:
target_width_smaller = smaller.width * params["scale"]
#
paramsSIFT1 = paramsSIFT.clone()
paramsSIFT1.maxOctaveSize = target_width_bigger
paramsSIFT1.minOctaveSize = int(paramsSIFT1.maxOctaveSize /
pow(2, paramsSIFT1.steps))
paramsSIFT2 = paramsSIFT.clone()
paramsSIFT2.maxOctaveSize = target_width_smaller
paramsSIFT2.minOctaveSize = int(paramsSIFT2.maxOctaveSize /
pow(2, paramsSIFT2.steps))
ijSIFT1 = SIFT(FloatArray2DSIFT(paramsSIFT1))
features1 = ArrayList() # of Point instances
ijSIFT1.extractFeatures(fp1, features1)
ijSIFT2 = SIFT(FloatArray2DSIFT(paramsSIFT2))
features2 = ArrayList() # of Point instances
ijSIFT2.extractFeatures(fp2, features2)
# Vector of PointMatch instances
sourceMatches = FloatArray2DSIFT.createMatches(
features1,
features2,
params.get(
"max_sd",
1.5), # max_sd: maximal difference in size (ratio max/min)
TranslationModel2D(),
params.get("max_id", Double.MAX_VALUE
), # max_id: maximal distance in image space
params.get("rod", 0.9)) # rod: ratio of best vs second best
# Store pointmatches
savePointMatches(os.path.basename(filepath1),
os.path.basename(filepath2), sourceMatches, csvDir,
params)
return True
except:
printException()
def ensurePointMatches(filepaths, csvDir, params, paramsSIFT, n_adjacent,
properties):
""" If a pointmatches csv file doesn't exist, will create it. """
w = ParallelTasks("ensurePointMatches",
exe=newFixedThreadPool(properties["n_threads"]))
exeload = newFixedThreadPool()
try:
if properties.get("use_SIFT", False):
syncPrintQ("use_SIFT is True")
# Pre-extract SIFT features for all images first
# ensureSIFTFeatures returns the features list so the Future will hold it in memory: can't hold onto them
# therefore consume the tasks in chunks:
chunk_size = properties["n_threads"] * 2
count = 1
for result in w.chunkConsume(
chunk_size, # tasks to submit before starting to wait for futures
(Task(ensureSIFTFeatures,
filepath,
paramsSIFT,
properties,
csvDir,
validateByFileExists=properties.get(
"SIFT_validateByFileExists"))
for filepath in filepaths)):
count += 1
if 0 == count % chunk_size:
syncPrintQ(
"Completed extracting or validating SIFT features for %i images."
% count)
w.awaitAll()
syncPrintQ(
"Completed extracting or validating SIFT features for all images."
)
# Compute pointmatches across adjacent sections
count = 1
for result in w.chunkConsume(
chunk_size,
generateSIFTMatches(filepaths, n_adjacent, params,
paramsSIFT, properties, csvDir)):
count += 1
syncPrintQ("Completed SIFT pointmatches %i/%i" %
(count, len(filepaths) * n_adjacent))
else:
# Use blockmatches
syncPrintQ("using blockmatches")
loadFPMem = SoftMemoize(lambda path: loadFloatProcessor(
path, params, paramsSIFT, scale=True),
maxsize=properties["n_threads"] +
n_adjacent)
count = 1
for result in w.chunkConsume(
properties["n_threads"],
pointmatchingTasks(filepaths, csvDir, params, paramsSIFT,
n_adjacent, exeload, properties,
loadFPMem)):
if result: # is False when CSV file already exists
syncPrintQ("Completed %i/%i" %
(count, len(filepaths) * n_adjacent))
count += 1
syncPrintQ("Awaiting all remaining pointmatching tasks to finish.")
w.awaitAll()
syncPrintQ("Finished all pointmatching tasks.")
except:
printException()
finally:
exeload.shutdown()
w.destroy()
def parseContent(self, page):
page = page.decode('gbk')
ret = {'stockBasicInfo': {}, 'stockOtherInfo': {}}
transMapCn2En = {
u'公司代码': 'compCode',
u'注册地址': 'registerAddr',
u'法定代表人': 'legalRepresentative',
u'董事会秘书姓名': 'boardSecretary',
u'E-mail': 'E-mail',
u'联系电话': 'phone',
u'网址': 'website',
u'SSE行业': 'sseSector',
u'是否上证180样本股': 'isSh180',
u'是否境外上市': 'isOverseasListing',
u'境外上市地': 'OverseasListingPlace'
}
try:
soup = BS(page)
titleSpan = soup.find('span', class_='pagetitle')
br = titleSpan.find('br')
cmpNameAndCode = br.previous_element
cmpName, code = re.split("\s+", cmpNameAndCode.strip())
table = soup.find('table',
width="100%",
cellspacing="5",
cellpadding="0",
border="0")
contentTd = table.find('td',
class_="content",
width="100%",
valign="top")
#contentTableList = contentTd.find_all('table', class="content", width="100%", bgcolor="#FFFFFF", align="center")
tdList = contentTd.find_all('td', class_="content_b")
for td in tdList:
key = re.sub(r"\s+", "", td.text.strip().strip(':'))
value = td.find_next_sibling('td').text.strip()
if key == u'股票代码(A股/B股)':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['code'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['B_code'] = ''
else:
ret['stockBasicInfo']['B_code'] = valueList[1]
elif key == u'上市日(A股/B股)':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['A_IPO_date'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['B_IPO_date'] = ''
else:
ret['stockBasicInfo']['B_IPO_date'] = valueList[1]
elif key == u'可转债简称（代码）':
valueListMatch = re.search(ur"(\.+)\s*（(.+)）", value)
if valueListMatch != None:
groups = valueListMatch.groups()
ret['stockBasicInfo']['convertibleBondAbbr'] = groups[
0]
ret['stockBasicInfo']['convertibleBondCode'] = groups[
1]
else:
ret['stockBasicInfo']['convertibleBondAbbr'] = ''
ret['stockBasicInfo']['convertibleBondCode'] = ''
elif key == u'公司简称(中/英)':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['compNameAbbr'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['compNameAbbrEn'] = ''
else:
ret['stockBasicInfo']['compNameAbbrEn'] = valueList[1]
elif key == u'公司全称(中/英)':
valueList = value.split("\n")
ret['stockBasicInfo']['compNameCn'] = valueList[0]
ret['stockBasicInfo']['compNameEn'] = valueList[1]
elif key == u'通讯地址（邮编）':
value = value.replace("\n", "")
valueListMatch = re.search(ur"(\.+)\s*（(.+)）", value)
if valueListMatch != None:
groups = valueListMatch.groups()
ret['stockBasicInfo']['contactAddr'] = groups[0]
ret['stockBasicInfo']['postcode'] = groups[1]
else:
ret['stockBasicInfo']['contactAddr'] = ''
ret['stockBasicInfo']['postcode'] = ''
elif key.startswith(u'CSRC行业'):
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['sector'] = "/".join(valueList)
ret['stockBasicInfo']['sector1'] = valueList[0]
ret['stockBasicInfo']['sector2'] = valueList[1]
if valueList[2] == '-':
ret['stockBasicInfo']['sector3'] = valueList[1]
else:
ret['stockBasicInfo']['sector3'] = valueList[2]
elif key == u'所属省/直辖市':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['province'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['city'] = ''
else:
ret['stockBasicInfo']['city'] = valueList[1]
elif key == u'A股状态/B股状态':
valueList = re.split(r"\s*/\s*", value)
ret['stockBasicInfo']['A_status'] = valueList[0]
if len(valueList) == 1 or valueList[1] == '-':
ret['stockBasicInfo']['B_status'] = ''
else:
ret['stockBasicInfo']['B_status'] = valueList[1]
else:
if key in transMapCn2En:
ret['stockBasicInfo'][
transMapCn2En[key]] = value.strip()
else:
ret['stockBasicInfo'][key] = value.strip()
except Exception, e:
util.printException()
return (None, e)
def savePointMatches(img_filename1,
img_filename2,
pointmatches,
directory,
params,
coords_header=["x1", "y1", "x2", "y2"]):
filename = basename(img_filename1) + '.' + basename(
img_filename2) + ".pointmatches.csv"
path = os.path.join(directory, filename)
msg = [str(len(pointmatches))]
ra = None
try:
"""
with open(path, 'w') as csvfile:
w = csv.writer(csvfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_NONNUMERIC)
# First two rows: parameter names and values
keys = params.keys()
msg.append("keys: " + ",".join(map(str, keys)))
msg.append("vals: " + ",".join(str(params[key]) for key in keys))
#for pm in pointmatches:
# msg.append(", ".join(map(str, PointMatches.asRow(pm))))
w.writerow(keys)
w.writerow(tuple(params[key] for key in keys))
# PointMatches header
if 0 == len(pointmatches):
# Can't know whether there are 2 or 3 dimensions per coordinate
w.writerow(coords_header)
else:
w.writerow(PointMatches.csvHeader(next(iter(pointmatches)))) # support both lists and sets
# One PointMatch per row
for pm in pointmatches:
w.writerow(PointMatches.asRow(pm))
# Ensure it's written
csvfile.flush()
os.fsync(csvfile.fileno())
"""
# DEBUG write differently, the above FAILS for ~20 out of 130,000 files
lines = []
keys = params.keys()
lines.append(",".join(map(str, keys)))
lines.append(",".join(map(str, (params[key] for key in keys))))
header = coords_header if 0 == len(pointmatches) \
else PointMatches.csvHeader(next(iter(pointmatches)))
lines.append(",".join(header))
for pm in pointmatches:
p1 = pm.getP1().getW() # a double[] array
p2 = pm.getP2().getW() # a double[] array
lines.append("%f,%f,%f,%f" % (p1[0], p1[1], p2[0], p2[1]))
body = "\n".join(lines)
ra = RandomAccessFile(path, 'rw')
ra.writeBytes(body)
ra.getFD().sync() # ensure it's written
except:
syncPrintQ("Failed to save pointmatches at %s\n%s" %
(path, "\n".join(msg)))
printException()
if os.path.exists(path):
os.remove(path)
finally:
if ra is not None:
ra.close()
def parseContent(self, page):
transMapCn2En = { \
u'公司代码': 'compCode',
u'公司简称': 'compNameAbbr',
u'公司全称': 'compNameCn',
u'英文名称': 'compNameEn',
u'注册地址': 'regAddr',
u'A股代码' : 'code',
u'A股简称' : 'nameCn',
u'A股上市日期': 'A_IPO_date',
u'A股总股本': 'A_totalShares',
u'A股流通股本':'A_circulationStock',
u'B股代码': 'B_code',
u'B股简称': 'B_nameCn',
u'B股上市日期': 'B_IPO_date',
u'B股总股本': 'B_totalShares',
u'B股流通股本': 'B_circulationStock',
u'地区': 'region',
u'省份': 'province',
u'城市': 'city',
u'所属行业': 'sector',
u'公司网址': 'webSite'
}
transMapEn2Cn = {}
for k in transMapCn2En:
transMapEn2Cn[transMapCn2En[k]] = k
ret = {'stockList':[], 'headerList':[]}
try:
reEmpty = re.compile(r'\s+')
soup = BS(page)
table = soup.find('table')
trList = table.find_all('tr')
trHeader = trList[0]
thList = trHeader.find_all('td')
headerList = [ reEmpty.sub('', td.text.strip()) for td in thList ]
ret['headerList'] = headerList
for tr in trList[1:]: # for each stock
tdList = tr.find_all('td')
tdTextList = [ td.text.strip() for td in tdList ]
stockDict = {}
for i in range(len(tdTextList)):
enKey = transMapCn2En[headerList[i]]
value = tdTextList[i]
if enKey in ('A_totalShares', 'A_circulationStock', 'B_totalShares', 'B_circulationStock'):# pull out the ','
value = value.replace(",", "")
stockDict[enKey] = tdTextList[i]
#J 金融业
if 'sector' in stockDict:
theSector = stockDict['sector']
stockDict['sectorCode'] = theSector[0]
stockDict['sectorName'] = theSector[1:]
ret['stockList'].append(stockDict)
except Exception, e:
util.printException()
return (None, e)