class RegPage(object):
def __init__(self, master=None):
self.root = master # 定义内部变量root
self.root.geometry('%dx%d' % (300, 200)) # 设置窗口大小
self.username = StringVar()
self.password = StringVar()
self.repassword = StringVar()
self.createPage()
self.mysqlClient = MysqlClient()
def createPage(self):
self.page = Frame(self.root) # 创建Frame
self.page.pack()
Label(self.page).grid(row=0, stick=W)
Label(self.page, text='账户: ').grid(row=1, stick=W, pady=10)
Entry(self.page, textvariable=self.username).grid(row=1,
column=1,
stick=E)
Label(self.page, text='密码: ').grid(row=2, stick=W, pady=10)
Entry(self.page, textvariable=self.password, show='*').grid(row=2,
column=1,
stick=E)
Label(self.page, text='确认密码: ').grid(row=3, stick=W, pady=10)
Entry(self.page, textvariable=self.repassword, show='*').grid(row=3,
column=1,
stick=E)
# Button(self.page, text='退出', command=self.page.quit).grid(row=3, column=1, stick=E)
Button(self.page, text='注册', command=self.register).grid(row=4,
column=1,
stick=E)
def register(self):
name = self.username.get()
password = self.password.get()
repassword = self.repassword.get()
if name.strip() == '' or password.strip() == '' or repassword.strip(
) == '':
showinfo(title='注册失败', message='账户名或者密码不能为空')
return
if password == repassword:
sql = "select * from user where(name='%s')" % (name)
find_res = self.mysqlClient.find_one(sql)
if find_res:
showinfo(title='错误', message='该用户已存在')
else:
sql = "insert into user(name,password) values ('%s','%s')" % (
name, password)
add_res = self.mysqlClient.save(sql)
if add_res:
showinfo(title='注册成功', message='注册成功')
self.page.destroy()
login = LoginPage.LoginPage(self.root)
else:
showinfo(title='注册失败', message='注册失败')
else:
showinfo(title='错误', message='两次输入的密码不一致')
class LoginPage(object):
def __init__(self, master=None):
self.root = master # 定义内部变量root
self.root.geometry('%dx%d' % (300, 180)) # 设置窗口大小
self.username = StringVar()
self.password = StringVar()
self.createPage()
self.mysqlClient = MysqlClient()
def createPage(self):
self.page = Frame(self.root) # 创建Frame
self.page.pack()
Label(self.page).grid(row=0, stick=W)
Label(self.page, text='账户: ').grid(row=1, stick=W, pady=10)
Entry(self.page, textvariable=self.username).grid(row=1,
column=1,
stick=E)
Label(self.page, text='密码: ').grid(row=2, stick=W, pady=10)
Entry(self.page, textvariable=self.password, show='*').grid(row=2,
column=1,
stick=E)
Button(self.page, text='登陆', command=self.loginCheck).grid(row=3,
stick=W,
pady=10)
# Button(self.page, text='退出', command=self.page.quit).grid(row=3, column=1, stick=E)
Button(self.page, text='注册', command=self.register).grid(row=3,
column=1,
stick=E)
def loginCheck(self):
name = self.username.get()
secret = self.password.get()
sql = "select * from user where(name='%s' and password='******')" % (
name, secret)
find_res = self.mysqlClient.find_one(sql)
if find_res:
self.page.destroy()
MainPage(self.root)
config.USERNAME = find_res[1]
else:
showinfo(title='错误', message='账号或密码错误！')
def register(self):
self.page.destroy()
RegPage(self.root)
class Scheduler(object):
def __init__(self):
self.download = Download()
self.db = MysqlClient()
self.redisClient = RedisClient()
def run(self):
#self.get_qu()
#self.get_zhen()
# self.push_url_to_redis()
self.get_position()
def get_qu(self):
sql = 'select * from shi'
results = self.db.find_all(sql)
for res in results:
shi_id = res[2]
url = SHI_URL.format(shi_id='c' + shi_id)
print(url)
html = self.download.get_html(url)
if html.status_code == 200 and html is not None:
html = HTML(html.text)
qu_id_list = html.xpath(
'//dl[@class="condition-district show-condition-district"]/dd/a/@href'
)
qu_name_list = html.xpath(
'//dl[@class="condition-district show-condition-district"]/dd/a/text()'
)
for qu_id, name in zip(qu_id_list[1:], qu_name_list[1:]):
qu_id = qu_id.split('/')
qu_id = qu_id[2]
sql = '''insert into qu(pid,qu_id,name) VALUES ('{pid}','{qu_id}','{name}')'''\
.format(pid=shi_id,qu_id=qu_id, name=name)
print(sql)
self.db.save(sql)
else:
print('该url无数据')
def get_zhen(self):
sql = 'select * from qu'
results = self.db.find_all(sql)
for res in results:
shi_id = res[1]
qu_id = res[2]
url = QU_URL.format(shi_id='c' + shi_id, qu_id=qu_id)
print(url)
html = self.download.get_html(url)
if html is not None and html.status_code == 200:
html = HTML(html.text)
zhen_id_list = html.xpath(
'//dl[@class="condition-area show-condition-area"]/dd/a/@href'
)
zhen_name_list = html.xpath(
'//dl[@class="condition-area show-condition-area"]/dd/a/text()'
)
for zhen_id, name in zip(zhen_id_list[1:], zhen_name_list[1:]):
zhen_id = zhen_id.split('/')
zhen_id = zhen_id[2]
sql = '''insert into zhen(pid,qu_id, zhen_id,name) VALUES ('{pid}','{qu_id}','{zhen_id}','{name}')'''\
.format(pid=shi_id,qu_id=qu_id,zhen_id=zhen_id, name=name)
print(sql)
self.db.save(sql)
else:
print('该url无数据')
def get_position(self):
redis_results = self.redisClient.pop('employment')
try:
json_obj = json.loads(redis_results[1].decode('utf8'))
except:
return None
if json_obj:
flag = True
pageToken = 1
#处理翻页问题
while flag:
detail_url_list = []
url = json_obj['url']
pre_page = re.search('\/\?page=(.*?)&', url).group(1)
if int(pageToken) > 10:
break
url = url.replace(
'page=' + pre_page + '&sort=2&ka=page-' + pre_page,
'page=' + str(pageToken) + '&sort=2&ka=page-' +
str(pageToken))
cityId = json_obj['cityId']
zhiweiId = json_obj['zhiweiId']
print(url)
html = self.download.get_html(url)
if html is not None and html.status_code == 200:
html = HTML(html.text)
#判断是否是当天发布，是的话请求详情页, 判断数据库是否有这条数据，有的话不请求（暂时）
li_xpath = html.xpath('//div[@class="job-list"]/ul/li')
for li in li_xpath:
content = etree.tostring(li)
content = HT.unescape(content.decode())
content = HTML(content)
li_time = content.xpath(
'string(//div[@class="info-publis"]/p)')
href_url = content.xpath(
'string(//div[@class="info-primary"]//h3/a/@href)')
try:
last_str = li_time.split('发布于')[1]
minute = last_str.split(':')[1]
#判断是否当天发布
if minute:
#判断数据库存不存在：
try:
cid = re.match('^/job_detail/(.*?)\.html',
href_url).group(1)
sql = "select * from positions where cid='%s'" % (
cid)
find_one_res = self.db.find_one(sql)
if find_one_res is None:
#先把cid插入，避免重复抓取
sql = "insert into positions(cid) values ('%s')" % (
cid)
self.db.save(sql)
detail_url_list.append(
config.HOST_URL + href_url)
elif find_one_res[2] is None:
detail_url_list.append(
config.HOST_URL + href_url)
else:
print('数据库存在该记录：' + str(cid))
except:
print('查询数据库出错：' + str(cid))
except:
print('该URL发布日期小于当天：' + config.HOST_URL + href_url)
results = self.get_detail(detail_url_list, cityId,
zhiweiId)
#判断是否翻页
try:
last_li = html.xpath(
'string(//div[@class="job-list"]/ul/li[last()]//div[@class="info-publis"]/p)'
)
last_str = last_li.split('发布于')[1]
minute = last_str.split(':')[1]
if minute:
pageToken = str(int(pageToken) + 1)
except:
flag = False
else:
print('该url无数据')
def get_detail(self, detail_url_list, cityId, zhiweiId):
for url in detail_url_list:
print('下载该详情页：' + url)
html = self.download.get_html(url)
if html is not None and html.status_code == 200:
html = HTML(html.text)
try:
cid = re.match(
'^https://www.zhipin.com/job_detail/(.*?)\.html',
url).group(1)
except:
print('获取cid失败')
continue
title = html.xpath('string(//h1)')
url = url
try:
publishDateStr = html.xpath(
'string(//span[@class="time"])').split('发布于')[1]
publishDate = int(
time.mktime(
time.strptime(publishDateStr, "%Y-%m-%d %H:%M")))
except:
publishDateStr = None
publishDate = None
try:
info = html.xpath(
'string(//div[@class="job-banner"]//div[@class="info-primary"]/p)'
)
info = info.split('：')
city = info[1][:-2]
jingyan = info[2][:-2]
xueli = info[3]
except:
city = None
jingyan = None
xueli = None
price = html.xpath(
'string(//div[@class="info-primary"]//span[@class="badge"])'
)
posterName = html.xpath('string(//h2)')
posterId = None
posterUrl = html.xpath(
'string(//div[@class="detail-figure"]/img/@src)')
content = html.xpath(
'string(//div[@class="job-sec"]/div[@class="text"])'
).strip()
try:
company_text = html.xpath(
'string(//a[@ka="job-cominfo"]/@href)')
companyID = re.match('/gongsi/(.*?)\.html',
company_text).group(1)
except:
companyID = None
createDate = int(time.time())
#判断是否是当天发布
temp_time = time.localtime(int(time.time()))
now_DateStr = time.strftime("%Y-%m-%d", temp_time)
lt = time.strptime(now_DateStr, "%Y-%m-%d")
now_timestamp = int(time.mktime(lt))
if publishDate == None or publishDate < now_timestamp or publishDate >= (
now_timestamp + 86400):
print('特例.该url不是当天发布：' + str(url))
continue
res_obj = {
'cid': cid,
'title': title,
'url': url,
'publishDateStr': publishDateStr,
'publishDate': publishDate,
'city': city,
'jingyan': jingyan,
'xueli': xueli,
'price': price,
'posterName': posterName,
'posterId': posterId,
'posterUrl': posterUrl,
'content': content,
'companyID': companyID,
'createDate': createDate,
'cityId': cityId,
'zhiweiId': zhiweiId
}
print(res_obj)
sql = "insert into positions(cid,title,url,publishDate,publishDateStr,city,jingyan,xueli,price,posterName,posterId,posterUrl,content,companyID,createDate,cityId, zhiweiId)" \
" VALUES ('%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s')" \
% (cid,title,url,publishDate,publishDateStr,city,jingyan,xueli,price,posterName,posterId,posterUrl,content,companyID,createDate,cityId, zhiweiId)\
+ "ON DUPLICATE KEY UPDATE title='%s', url='%s', publishDate='%s', publishDateStr='%s', city='%s', jingyan='%s', xueli='%s', price='%s', posterName='%s', posterId='%s', posterUrl='%s', content='%s', companyID='%s', createDate='%s',cityId='%s', zhiweiId='%s'" \
%(title,url,publishDate,publishDateStr,city,jingyan,xueli,price,posterName,posterId,posterUrl,content,companyID,createDate,cityId, zhiweiId)
self.db.save(sql)
else:
print('请求详情页失败：' + str(url))
def push_url_to_redis(self):
# zhiwei_list = []
# zhiwei_sql = 'select * from zhiwei'
# zhiwei_results = self.db.find_all(zhiwei_sql)
# for zhiwei in zhiwei_results:
# zhiwei_list.append(zhiwei[2])
#
# zhen_sql = 'select * from zhen'
# zhen_results = self.db.find_all(zhen_sql)
#
# for res in zhen_results:
# pid = res[1]
# zhen_id = res[2]
# for zhiwei_id in zhiwei_list:
# url = POSITION_URL.format(pid=pid, zhen_id=zhen_id, zhiwei_id=zhiwei_id, pageToken='1')
# self.redisClient.push('employment',url)
zhiwei_list = []
zhiwei_sql = 'select * from zhiwei'
zhiwei_results = self.db.find_all(zhiwei_sql)
for zhiwei in zhiwei_results:
zhiwei_list.append(zhiwei[2])
shi_sql = 'select * from shi'
shi_results = self.db.find_all(shi_sql)
for res in shi_results:
pid = res[2]
for zhiwei_id in zhiwei_list:
url = NEW_POSITION_URL.format(pid=pid,
zhiwei_id=zhiwei_id,
pageToken='1')
url_obj = {"url": url, "cityId": pid, "zhiweiId": zhiwei_id}
self.redisClient.push('employment', json.dumps(url_obj))
class InputFrame(Frame): # 继承Frame类
def __init__(self, master=None):
Frame.__init__(self, master)
self.root = master # 定义内部变量root
self.word = StringVar()
self.mean = StringVar()
self.createPage()
self.mysqlClient = MysqlClient()
self.spider = spider.Spider()
def createPage(self,
query_res={
'fanyi': '',
'phonetic': '',
'translation': ''
}):
# self.fm2 = Frame(self.root)
# Button(self, text='Left').pack(side=LEFT)
# Button(self, text='This is the Center button').pack(side=LEFT)
# Button(self, text='Right').pack(side=LEFT)
# self.fm2.pack(side=LEFT, padx=10)
Label(self).grid(row=0, stick=W, pady=10)
Label(self, text='请输入: ').grid(row=1, stick=W, pady=10)
Entry(self, textvariable=self.word, width=40).grid(row=2, stick=W)
Label(self, text='结果如下: ').grid(row=4, stick=W, pady=10)
Label(self,
text='翻译：' + query_res['fanyi'],
height=2,
width=40,
justify='left').grid(row=5, stick=W, pady=10)
Label(self,
text='发音：' + query_res['phonetic'],
height=2,
width=40,
justify='left').grid(row=6, stick=W, pady=10)
Label(self,
text='其他：' + query_res['translation'],
height=2,
width=40,
justify='left').grid(row=7, stick=W, pady=10)
# Entry(self, textvariable=self.mean).grid(row=3, column=1, stick=E)
# Text(self, height=5, width=50).grid(row=4, column=1, stick=W)
Button(self, text='查询', command=self.query_word).grid(row=10,
column=1,
stick=E,
pady=10)
Button(self, text='收藏', command=self.collect_word).grid(row=10,
column=2,
stick=E,
pady=10)
def query_word(self):
word = self.word.get()
#是英文
eng = '1'
# 是中文
if '\u4e00' <= word[0] <= '\u9fff':
eng = '0'
#先判断在不在当前数据库，不在再用360翻译接口
sql1 = "select * from words where en_word like '%s'" % (word)
find_res1 = self.mysqlClient.find_one(sql1)
sql2 = "select * from words where cn_word like '%s'" % (word)
find_res2 = self.mysqlClient.find_one(sql2)
if find_res1:
query_res = {
'fanyi': find_res1[2],
'phonetic': '',
'translation': '',
}
self.createPage(query_res)
elif find_res2:
query_res = {
'fanyi': find_res2[1],
'phonetic': '',
'translation': '',
}
self.createPage(query_res)
else:
query_res = self.spider.get_dic(word, eng=eng)
if query_res:
self.createPage(query_res)
else:
showinfo(title='查询失败', message='查询失败，请检查您的网络')
#添加到历史查询记录
name = config.USERNAME
mean = json.dumps(query_res['fanyi'])
mytime = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime())
timestamp = int(time.time())
sql = "insert into history(word,mean,name,time,timestamp) values('%s','%s','%s','%s','%s')" % (
word, mean, name, mytime, timestamp)
print(sql)
self.mysqlClient.save(sql)
def collect_word(self):
word = self.word.get()
# 是英文
eng = '1'
# 是中文
if '\u4e00' <= word[0] <= '\u9fff':
eng = '0'
# 先判断在不在当前数据库，不在再用360翻译接口
sql1 = "select * from words where en_word like '%s'" % (word)
find_res1 = self.mysqlClient.find_one(sql1)
sql2 = "select * from words where cn_word like '%s'" % (word)
find_res2 = self.mysqlClient.find_one(sql2)
if find_res1:
query_res = {
'fanyi': find_res1[2],
'phonetic': '',
'translation': '',
}
self.createPage(query_res)
elif find_res2:
query_res = {
'fanyi': find_res2[1],
'phonetic': '',
'translation': '',
}
self.createPage(query_res)
else:
query_res = self.spider.get_dic(word, eng=eng)
if query_res:
self.createPage(query_res)
else:
showinfo(title='查询失败', message='查询失败，请检查您的网络')
# 添加到我的收藏
name = config.USERNAME
mean = str(query_res['fanyi'])
mytime = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime())
timestamp = int(time.time())
sql = "insert into collection(word,mean,name,time,timestamp) values('%s','%s','%s','%s','%s')" % (
word, mean, name, mytime, timestamp)
print(sql)
save_res = self.mysqlClient.save(sql)
if save_res:
showinfo(title='成功', message='收藏成功')
else:
showinfo(title='失败', message='收藏失败！')