用 Python 给自己找个合适的妹子

# coding=utf-8
from selenium import webdriver
import time
from lxml import etree
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
"""
PEP8 Python编程规范
https://www.douban.com/note/134971609/
"""
# 获取浏览器驱动
driver = webdriver.Firefox()
driver.maximize_window()
webUrl = 'http://www.lovewzly.com/jiaoyou.html'
driver.get(webUrl)
# 等15秒，我来手动做一下筛选条件。，女性，21-30左右，学历本科，
# 本来想通过js代码，来自动执行，但无奈对js真的不熟，也没有太多时间去整了，凑合看看.
time.sleep(15)
"""
下拉滚动条，从1开始到3结束 分2次加载完每页数据
"""
while True:
for i in range(1, 20):
height = 1000 * i # 每次滑动20000像素
strword = "window.scrollBy(0," + str(height) + ")"
driver.execute_script(strword)
time.sleep(3)
s = etree.HTML(driver.page_source)
selectors = s.xpath('//*[@id="hibox"]/table/tbody/tr/td/div')
with open('内心读白.txt', 'a') as f:
for selector in selectors:
img = selector.xpath('./div[1]/img/@src')
nick = selector.xpath('./div[2]/p[1]/span/text()')
age = selector.xpath('./div[2]/p[2]/span[1]/text()')
height = selector.xpath('./div[2]/p[2]/span[2]/text()')
address = selector.xpath('./div[2]/p[2]/span[3]/text()')
heart = selector.xpath('./div[2]/p[3]/text()')
img = img[0] if len(img) > 0 else ''
nick = nick[0] if len(nick) > 0 else ''
age = age[0] if len(age) > 0 else ''
height = height[0] if len(height) > 0 else ''
address = address[0] if len(address) > 0 else ''
heart = heart[0] if len(heart) > 0 else ''
print nick, age, height, address, heart, img
f.write(heart)

def craw_data(self):
'''数据抓取'''
headers = {
'Referer': 'http://www.lovewzly.com/jiaoyou.html',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4620.400 QQBrowser/9.7.13014.400'
}
page = 1
while True:
query_data = {
'page':page,
'gender':self.gender,
'starage':self.stargage,
'endage':self.endgage,
'stratheight':self.startheight,
'endheight':self.endheight,
'marry':self.marry,
'salary':self.salary,
}
url = 'http://www.lovewzly.com/api/user/pc/list/search?'+urllib.urlencode(query_data)
print url
req = urllib2.Request(url, headers=headers)
response = urllib2.urlopen(req).read()
# print response
self.parse_data(response)
page += 1

def parse_data(self,response):
'''数据解析'''
persons = json.loads(response).get('data').get('list')
if persons is None:
print '数据已经请求完毕'
return
for person in persons:
nick = person.get('username')
gender = person.get('gender')
age = 2018 - int(person.get('birthdayyear'))
address = person.get('city')
heart = person.get('monolog')
height = person.get('height')
img_url = person.get('avatar')
education = person.get('education')
print nick,age,height,address,heart,education
self.store_info(nick,age,height,address,heart,education,img_url)
self.store_info_execl(nick,age,height,address,heart,education,img_url)

def store_info(self, nick,age,height,address,heart,education,img_url):
'''
存照片,与他们的内心独白
'''
if age < 22:
tag = '22岁以下'
elif 22 <= age < 28:
tag = '22-28岁'
elif 28 <= age < 32:
tag = '28-32岁'
elif 32 <= age:
tag = '32岁以上'
filename = u'{}岁_身高{}_学历{}_{}_{}.jpg'.format(age,height,education, address, nick)
try:
# 补全文件目录
image_path = u'E:/store/pic/{}'.format(tag)
# 判断文件夹是否存在。
if not os.path.exists(image_path):
os.makedirs(image_path)
print image_path + ' 创建成功'
# 注意这里是写入图片，要用二进制格式写入。
with open(image_path + '/' + filename, 'wb') as f:
f.write(urllib.urlopen(img_url).read())
txt_path = u'E:/store/txt'
txt_name = u'内心独白.txt'
# 判断文件夹是否存在。
if not os.path.exists(txt_path):
os.makedirs(txt_path)
print txt_path + ' 创建成功'
# 写入txt文本
with open(txt_path + '/' + txt_name, 'a') as f:
f.write(heart)
except Exception as e:
e.message

def store_info_execl(self,nick,age,height,address,heart,education,img_url):
person = []
person.append(self.count) #正好是数据条
person.append(nick)
person.append(u'女' if self.gender == 2 else u'男')
person.append(age)
person.append(height)
person.append(address)
person.append(education)
person.append(heart)
person.append(img_url)
for j in range(len(person)):
self.sheetInfo.write(self.count, j, person[j])
self.f.save(u'我主良缘.xlsx')
self.count += 1
print '插入了{}条数据'.format(self.count)