def tujiParse2(self, info, urlSign, page, url, domain):
encoding, picUrl, title, text, publishTime, mypos, pageNum = tupian.parse(
url, page, info)
images = [picUrl]
if info.has_key('detailFenyePattern'):
if pageNum > 1:
for i in range(2, pageNum + 1):
urlNew = url.replace(info['detailFenyePattern'][0],
info['detailFenyePattern'][1] % i)
page = getPage(urlNew)
if not page:
retStatus = self.changeStatus(urlSign, 1)
print 'down url:%s failed' % urlNew
continue
fenyeEncoding, fenyePicUrl, fenyeTitle, fenyeText, fenyePublishTime, fenyeMypos, fenyePageNum = tupian.parse(
url, page, info)
text = text + fenyeText
images.append(fenyePicUrl)
if not publishTime:
x = time.localtime(time.time())
publishTime = '0000-00-00 00:00:00'
text = text.replace('\r', '').replace('\n', ' ').replace('\t', '')
picInfo = []
if len(images) == 0:
retStatus = self.changeStatus(urlSign, 1)
print 'url:%s has no pic' % url
return False
for i in range(len(images)):
picInfo.append({'picUrl': images[i], 'picDesc': '', 'pic_seq': i})
imgJson = json.dumps(picInfo, ensure_ascii=False)
sql = "update tbl_content_2 set title = '%s', publishTime = '%s', status = 2, text = '%s', mypos = '%s', images = '%s' where urlSign = '%s'"\
%(MySQLdb.escape_string(title.encode('utf-8')), publishTime.encode('utf-8'), MySQLdb.escape_string(text.encode('utf-8')), MySQLdb.escape_string(mypos.encode('utf-8')), imgJson.encode('utf-8'), urlSign.encode('utf-8'))
print sql
doDB(sql, 'chuilei')
return True
def run(self, domain, info):
sql = "select urlSign, url, domain, isAlbum from tbl_content_2 where domain = '%s' \
and status = 0 and category='%s';" % (domain, info['category'])
res = getDB(sql, 'chuilei')
for item in res:
urlSign = item[0]
url = item[1]
print url
domain = item[2]
isAlbum = item[3]
page = getPage(url)
#page = page.decode('utf-8','ignore')
if not page:
retStatus = self.changeStatus(urlSign, 1)
print 'down url:%s failed' % url
continue
if isAlbum == 0:
ret = self.tupianParse(info, urlSign, page, url, domain)
if not ret:
retStatus = self.changeStatus(urlSign, 1)
print 'parse url:%s failed' % url
continue
elif isAlbum == 1:
ret = self.tujiParse(info, urlSign, page, url, domain)
if not ret:
retStatus = self.changeStatus(urlSign, 1)
print 'parse url:%s failed' % url
continue
elif isAlbum == 2:
ret = self.tujiParse2(info, urlSign, page, url, domain)
if not ret:
retStatus = self.changeStatus(urlSign, 1)
print 'parse url:%s failed' % url
continue
def getDetailUrl(self, fenyeUrl, info):
page = getPage(fenyeUrl)
detailUrlList = self.parse(fenyeUrl, page, info['urlPattern'])
if not detailUrlList:
print 'url:%s can not get detail page url' % fenyeUrl
return False
self.process(fenyeUrl, detailUrlList, info)
return True
def getSourceFy(self, sourceUrl, info):
fyList = []
page = getPage(sourceUrl)
if not page:
return fyList
pageNum = pe.pageNumExtract(page, info['domain'])
fyList.append(sourceUrl)
if pageNum > 1:
for i in range(2, pageNum + 1):
if info['sourceFenyePattern'][0] == "":
urlNew = sourceUrl + info['sourceFenyePattern'][1] % i
else:
urlNew = sourceUrl.replace(
info['sourceFenyePattern'][0],
info['sourceFenyePattern'][1] % i)
fyList.append(urlNew)
return fyList
#encoding: utf-8
import sys
import content_extract as ce
sys.path.append("../../lib")
import download
if __name__ == "__main__":
html = download.getPage(sys.argv[1])
enc, time, title, text = ce.parse(sys.argv[1], html)
print "标题：" + title.encode('utf-8', 'ignore')
print "时间：" + time.encode('utf-8', 'ignore')
print '=' * 10
print "内容：" + text.encode('utf-8', 'ignore')
time = strtotime(time, '')
if webInfo.has_key('imgReplace'):
patternList = webInfo['imgReplace']
for picUrl in images:
for pattern in patternList:
picUrl = picUrl.replace(pattern[0], pattern[1])
imgList.append(picUrl)
else:
imgList = images
#print time.encode('utf-8')
#print text.encode('utf-8')
return encoding, title, text, time, imgList, mypos
if __name__ == "__main__":
from original_url_sucai import webInfo
#html = open('page.html').read()
#enc, title, text, time, images, mypos = parse('http://www.guandongphoto.com/thread-1035924-1-11.html',html, webInfo['guandongphoto.com'])
url = sys.argv[1]
domain = sys.argv[2]
html = getPage(url)
enc, title, text, time, images, mypos = parse(url, html, webInfo[domain])
print "标题：" + title.encode('utf-8', 'ignore')
print "mypos：" + mypos.encode('utf-8', 'ignore')
print "时间：" + time.encode('utf-8', 'ignore')
print "内容：\n" + text.encode('utf-8', 'ignore')
print '=' * 10
print '图片:'
print images
import sys
import re
import datetime
sys.path.append("../lib")
from download import getPage
from clientSource import *
webInfo = {
'category': '美图',
'sourceName': '中关村在线',
'domain': 'zol.com',
'sourceUrl': 'http://sj.zol.com.cn/bizhi/',
'urlPattern': 'http.*/bizhi/.*\.html',
}
client = Client()
for i in range(2, 430):
url = "http://www.5857.com/list-11-0-0-0-0-0-%d.html" % i
print url
page = getPage(url)
if not page:
print 'down url:%s failed' % url
continue
client.parse(page, webInfo['sourceUrl'], webInfo['category'],
webInfo['sourceName'], webInfo['domain'],
webInfo['urlPattern'])
#page = open('./page').read()
#client = Client()
#client.parse(page, webInfo['sourceUrl'], webInfo['category'], webInfo['sourceName'], webInfo['domain'], webInfo['urlPattern'])