def addCol():
column = request.args.get('newCol')
if column:
#g_all_fields.append(column)
add_col_sql = ADD_COLUMN_SQL % (session['tables'][0], column)
with DbHandler(DB_NAME) as db:
db.execute_sql(add_col_sql)
return redirect(url_for('index'))
def userConfig():
newPword = request.form["newPword"]
if newPword:
with DbHandler(DB_NAME) as db:
curUser = session.get('user')
update_sql = UPDATE_USER_PASSWORD_SQL % (newPword, curUser)
db.execute_sql(update_sql)
return redirect(url_for('logout'))
return redirect(url_for('index'))
def show_image():
field = list(request.args.values())[0]
with DbHandler(DB_NAME) as db:
df = pd.read_sql(
"select {field} from {table}".format(field=field,
table=session.get(
'tables', [])[0]),
db.conn)
counts = counts_max(df[field], 10)
print_pie(counts, field)
return redirect(url_for("images"))
def output():
tables = session.get('tables', [])
coding = list(request.args.values())[0]
print("this is output process", tables)
print("this is choosing the encoding format:", coding)
with DbHandler(DB_NAME) as db:
pd_csv = pd.read_sql("select * from {table}".format(table=tables[0]),
db.conn)
pd_csv.to_csv("{}.csv".format(tables[0]), encoding=coding)
filename = "{}.csv".format(tables[0])
if os.path.exists(filename):
print("this is output**********")
return send_from_directory(r'./', filename, as_attachment=True)
from dbHandler import DbHandler
from model import *
v = Vertex(12, 12, 12, 0)
h = DbHandler('sqlite+pysqlite:///database.db')
h.add(v)
h.commit()
print(h.vertices)
def run(self):
with self.threadingSum:
logging.debug("%s start" % self.url)
dbHandler = DbHandler()
if not dbHandler.hasQuestion(self.url):
# 插入新的问题
question = Question(self.url)
title = question.get_title()
detail = question.get_detail()
answerNum = question.get_answer_num()
followersNum = question.get_followers_num()
tags = ""
for tag in question.get_tags():
tags += tag + ";"
tags = tags[0: len(tags) - 1]
questionDict = {"url": self.url, "title": title,
"detail": detail, "followers": followersNum,
"answerNum": answerNum, "tags": tags}
dbHandler.insertNewQuestion(questionDict)
zh_qid = dbHandler.getQueIdByUrl(self.url)
# 插入新的答案
for answer_link in question.get_all_answer_link():
answer = Answer(answer_link)
author = answer.get_author()
votes = answer.get_votes()
answerDict = {"url": answer_link, "author": author, "zh_qid": zh_qid,
"votes": votes}
dbHandler.insertNewAnswer(answerDict)
# 插入图片地址
zh_aid = dbHandler.getAnsIdByUrl(answer_link)
for imgUrl in answer.get_all_pics():
dbHandler.insertNewImgUrl(zh_aid, imgUrl)
contents = answer.get_answer_content()
self.storeTheAnswer(zh_aid, contents)
dbHandler.close()
logging.debug("%s done" % self.url)
def __init__(self):
self.dbHandler = DbHandler()
class ToHtml:
def __init__(self):
self.dbHandler = DbHandler()
def createHtml(self):
html_tpl = u'''<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="zh-CN">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="provider" content="www.cnepub.com"/>
<meta name="builder" content="epubBuilder present by www.cnepub.com"/>
<meta name="right" content="该文档由epubBuilder生成。epubBuilder为掌上书苑（www.cnepub.com)提供的epub制作工具，仅供个人交流与学习使用。在未获得掌上书苑的商业授权前，不得用于任何商业用途。"/>
<link rel="stylesheet" type="text/css" href="css/main.css"/>
<title>%(title)s</title>
</head>
<body>
<center>
<h3>%(title)s</h3>
</center>
<hr>
<div class="band">
%(band)s
</div>
<div class="answer-content">
%(content)s
</div>
</body>
'''
questions = self.dbHandler.getQuestions()
utils = Utils()
for question in questions:
zh_qid = question["zh_qid"]
q_url = question["url"]
title = question["title"]
detail = question["detail"]
tags = question["tags"]
followers = question["followers"]
answerNum = question["answerNum"]
band = ""
band += '<div class = "tags">\n'
for tag in tags.split(";"):
band += '<span>' + tag + '</span>\n'
band += '</div>\n'
band += '<div class = "info"><span><strong>%d</strong>个回答</span><span><strong>%d</strong>人关注该问题</span></div>\n' % (answerNum, followers)
band += '<div class = "detail">' + detail + '</div>\n'
band += '<div class = "url">原问题网址：<a href="' + q_url + '"><h4>' + q_url + '</h4></a></div>\n'
contents = ""
answers = self.dbHandler.getAnswersByQid(zh_qid)
for answer in answers:
zh_aid = answer["zh_aid"]
author = answer["author"]
votes = answer["votes"]
contents += '<div class = "content">'
contents += '<span id = "author">%s</span>\n' % author
contents += '<span id = "votes">赞同: %s</span>\n' % votes
tmp_txt_dir = utils.get("tmp_answer_content_dir")
with open(os.getcwd() + tmp_txt_dir + "%s.txt" % (zh_aid), 'r') as txt:
contents += str(txt.read())
contents += "\n"
contents += '</div>'
tmp_html_dir = utils.get("tmp_answer_content_dir") + 'html'
print tmp_html_dir
html = open(os.getcwd() + tmp_html_dir + "/" + title + ".html", 'w')
html.write(html_tpl % {'title': title, 'band': band, 'content': contents})
def __init__(self, threadingSum, url):
threading.Thread.__init__(self)
self.dbHandler = DbHandler()
self.url = url
self.threadingSum = threadingSum
with self.threadingSum:
logging.debug("%s start!" % self.url)
pic_name = self.url.split("/")[-1]
request = requests.get(self.url, stream=True, timeout=10)
with open(os.getcwd() + "/tmp/html/images/" + pic_name,
'wb') as fd:
for chunk in request.iter_content():
fd.write(chunk)
logging.debug("%s done!" % self.url)
if __name__ == '__main__':
#设置线程数
threadingSum = threading.Semaphore(20)
dbHandler = DbHandler()
question = Question("http://www.zhihu.com/question/26702926")
answer = Answer("http://www.zhihu.com/question/26702926/answer/33843851")
img_urls = answer.get_all_pics()
for url in img_urls:
t = DownloadImg(threadingSum, url)
t.start()
for t in threading.enumerate():
if t is threading.currentThread():
continue
t.join()
