def score():
jsonData = json.loads(request.data.decode())
buffer = jsonData["buffer"]
image = Util.to_binary(jsonData["buffer"]).convert('RGB')
result = scoring(image)
array = more(buffer, jsonData["gender"], result)
return json.dumps({'score': str(round(result, 2)), 'result': array}), 200
from urlspecify.urlsingle_fc import Urlsingle
import chardet
import re
import os
import logging
import sys
import atexit
import json
global gstart_page
global gstart_pos
#单例类初始化
sigle = Urlsingle()
util = Util()
pc = Pycrawl()
#log 初始化
logging.basicConfig(filename='log\\2.24.log', level=logging.DEBUG)
header_dic = {}
header_dic['User-Agent'] = sigle._useragent_c
header_dic['Cookie'] = sigle._cookie_c
header_dic_ajax = {}
header_dic_ajax['User-Agent'] = sigle._useragent_c
header_dic_ajax['Cookie'] = sigle._cookie_c
header_dic_ajax['Referer'] = sigle._referer
header_dic_pic = {}
#pic_reg = '<div class="c cl">(?:.*?)<a href="'+single._rooturl+'(.*?)" onclick="atarget\(this\)" title="(.*?)" class="z">(?:.*?)<img src="http://(.*?)" alt'
pic_reg = '<div class="c cl">(?:.*?)<a href="'+single._rooturl+'(.*?)" onclick="atarget\(this\)" title="(.*?)" class="z">(?:.*?)<img src="(.*?)"'
print pic_reg
patten = re.compile(pic_reg, re.S)
#f=open('out.txt','w')
#print >>f,html_content
return patten.findall(html_content)
def get_code(html_content):
reg = '<tbody>(?:.*?)<td>(.*?)</td>'
patten = re.compile(reg,re.S)
return patten.findall(html_content)[0]
#单例类初始化
urlsingle = Urlsingle()
util = Util()
pc = Pycrawl()
header_dic ={}
header_dic['User-Agent'] = urlsingle._useragent_f
for index in range(1,18):
url = urlsingle._scrapyurl%index
html_content = pc.get_url_content(header_dic,url)
# print chardet.detect(html_content) #GB2312
if html_content:
#f=open('out.txt','w')
#print >>f,html_content
ret = get_pic_title_and_url(html_content)
# print len(ret)
save_path = "savejpdir\\"+str(index)+"\\"
#所爬取的网站utf-8编码
#notice表示需要注意的地方
#custom表示每个程序对于这个地方需要手工修改一下
#import重要总结
import re
import os
import logging
import sys
import chardet
from classes.pycrawl import Pycrawl
from classes.util import Util
from urlspecify.urlsingle_pmj import Urlsingle
pc = Pycrawl()
util = Util()
urlsingle = Urlsingle()
logging.basicConfig(filename='log\\pmj_d.log',level=logging.DEBUG)
header_dic ={}
header_dic['User-Agent'] = urlsingle._useragent_c
header_dic['Cookie'] = urlsingle._cookie_c
def get_urls(content):
reg = '<img src="(.*?)"'
patten = re.compile(reg, re.S)
return patten.findall(content)
def get_pics(html_content):
import json
import os
from classes.crawl import Crawl
from classes.crawl_result import CrawlResult
from classes.util import Util
from string import Template
uti = Util()
def list(event, contenxt):
results = uti.get_all_saved_results()
content = ""
for result in results:
content += "<li> " + result["title"] + "<br /><a href='" + result["s3_path"] + "'>" + result["page_name"] + "</a> Created: " + result["created"] +"<br />"
content += "<p> Original Link:" + result['crawl_url'] + "</p>"
content += "</li></hr />"
template = """
<html>
<head><title>Web Alert Results</title></head>
<body>
<h1>Web Alert Results</h1>
<ul>
"""
template += content
template += """
import atexit
import json
from xlutils.copy import copy
from xlrd import open_workbook
from xlwt import easyxf
import xlwt
global gstart_page
global gstart_pos
global gstart_line
#单例类初始化
sigle = Urlsingle()
util = Util()
pc = Pycrawl()
#log 初始化
logging.basicConfig(filename='log\\fca.t.log', level=logging.DEBUG)
header_dic = {}
header_dic['User-Agent'] = sigle._useragent_c
header_dic['Cookie'] = sigle._cookie_c
header_dic_ajax = {}
header_dic_ajax['User-Agent'] = sigle._useragent_c
header_dic_ajax['Cookie'] = sigle._cookie_c
header_dic_ajax['Referer'] = sigle._referer