Python爬虫抓取微博评论
第一步：引入库
import time
import base64
import rsa
import binascii
import requests
import re
from PIL import Image
import random
from urllib.parse import quote_plus
import http.cookiejar as cookielib
import csv
import os
第二步：一些全局变量的设置
comment_path = 'comment'
agent = 'mozilla/5.0 (windowS NT 10.0; win64; x64) appLewEbkit/537.36 (KHTML, likE gecko) chrome/71.0.3578.98 safari/537.36'
headers = {'User-Agent': agent}
第三步：创立目录作为存放数据的
if not os.path.exists(comment_path):
os.mkdir(comment_path)
第四步：登陆类的创立
class WeiboLogin(object):
"""
通过登录 weibo.com 然后跳转到 m.weibo.cn
""" # 初始化数据
def __init__(self, user, password, cookie_path):
super(WeiboLogin, self).__init__()
self.user = user
self.password = password
self.session = requests.Session()
self.cookie_path = cookie_path
# LWPCookieJar是python中管理cookie的工具，可以将cookie保存到文件，或者在文件中读取cookie数据到程序
self.session.cookies = cookielib.LWPCookieJar(filename=self.cookie_path)
self.index_url = "http://weibo.com/login.php"
self.session.get(self.index_url, headers=headers, timeout=2)
self.postdata = dict() def get_su(self):
"""
对 email 地址和手机号码 先 javascript 中 encodeURIComponent
对应 Python 3 中的是 urllib.parse.quote_plus
然后在 base64 加密后decode
"""
username_quote = quote_plus(self.user)
username_base64 = base64.b64encode(username_quote.encode("utf-8"))
return username_base64.decode("utf-8") # 预登陆获得 servertime, nonce, pubkey, rsakv
def get_server_data(self, su):
"""与原来的相比，微博的登录从 v1.4.18 升级到了 v1.4.19
这里使用了 URL 拼接的方式，也可以用 Params 参数传递的方式
"""
pre_url = "http://login.sina.com.cn/sso/prelogin.php?entry=weibo&callback=sinaSSOController.preloginCallBack&su="
pre_url = pre_url + su + "&rsakt=mod&checkpin=1&client=ssologin.js(v1.4.19)&_="
pre_url = pre_url + str(int(time.time() * 1000))
pre_data_res = self.session.get(pre_url, headers=headers)
# print("*"*50)
# print(pre_data_res.text)
# print("*" * 50)
sever_data = eval(pre_data_res.content.decode("utf-8").replace("sinaSSOController.preloginCallBack", '')) return sever_data def get_password(self, servertime, nonce, pubkey):
"""对密码进行 RSA 的加密"""
rsaPublickey = int(pubkey, 16)
key = rsa.PublicKey(rsaPublickey, 65537) # 创建公钥
message = str(servertime) + '\t' + str(nonce) + '\n' + str(self.password) # 拼接明文js加密文件中得到
message = message.encode("utf-8")
passwd = rsa.encrypt(message, key) # 加密
passwd = binascii.b2a_hex(passwd) # 将加密信息转换为16进制。
return passwd def get_cha(self, pcid):
"""获取验证码，并且用PIL打开，
1. 如果本机安装了图片查看软件，也可以用 os.subprocess 的打开验证码
2. 可以改写此函数接入打码平台。
"""
cha_url = "https://login.sina.com.cn/cgi/pin.php?r="
cha_url = cha_url + str(int(random.random() * 100000000)) + "&s=0&p="
cha_url = cha_url + pcid
cha_page = self.session.get(cha_url, headers=headers)
with open("cha.jpg", 'wb') as f:
f.write(cha_page.content)
f.close()
try:
im = Image.open("cha.jpg")
im.show()
im.close()
except Exception as e:
print(u"请到当前目录下，找到验证码后输入") def pre_login(self):
# su 是加密后的用户名
su = self.get_su()
sever_data = self.get_server_data(su)
servertime = sever_data["servertime"]
nonce = sever_data['nonce']
rsakv = sever_data["rsakv"]
pubkey = sever_data["pubkey"]
showpin = sever_data["showpin"] # 这个参数的意义待探索
password_secret = self.get_password(servertime, nonce, pubkey) self.postdata = {
'entry': 'weibo',
'gateway': '',
'from': '',
'savestate': '',
'useticket': '',
'pagerefer': "https://passport.weibo.com",
'vsnf': '',
'su': su,
'service': 'miniblog',
'servertime': servertime,
'nonce': nonce,
'pwencode': 'rsa2',
'rsakv': rsakv,
'sp': password_secret,
'sr': '1366*768',
'encoding': 'UTF-8',
'prelt': '',
"cdult": "",
'url': 'http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack',
'returntype': 'TEXT' # 这里是 TEXT 和 META 选择，具体含义待探索
}
return sever_data def login(self):
# 先不输入验证码登录测试
try:
sever_data = self.pre_login()
login_url = 'https://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)&_'
login_url = login_url + str(time.time() * 1000)
login_page = self.session.post(login_url, data=self.postdata, headers=headers)
ticket_js = login_page.json()
ticket = ticket_js["ticket"]
except Exception as e:
sever_data = self.pre_login()
login_url = 'https://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)&_'
login_url = login_url + str(time.time() * 1000)
pcid = sever_data["pcid"]
self.get_cha(pcid)
self.postdata['door'] = input(u"请输入验证码")
login_page = self.session.post(login_url, data=self.postdata, headers=headers)
ticket_js = login_page.json()
ticket = ticket_js["ticket"]
# 以下内容是 处理登录跳转链接
save_pa = r'==-(\d+)-'
ssosavestate = int(re.findall(save_pa, ticket)[0]) + 3600 * 7
jump_ticket_params = {
"callback": "sinaSSOController.callbackLoginStatus",
"ticket": ticket,
"ssosavestate": str(ssosavestate),
"client": "ssologin.js(v1.4.19)",
"_": str(time.time() * 1000),
}
jump_url = "https://passport.weibo.com/wbsso/login"
jump_headers = {
"Host": "passport.weibo.com",
"Referer": "https://weibo.com/",
"User-Agent": headers["User-Agent"]
}
jump_login = self.session.get(jump_url, params=jump_ticket_params, headers=jump_headers)
uuid = jump_login.text uuid_pa = r'"uniqueid":"(.*?)"'
uuid_res = re.findall(uuid_pa, uuid, re.S)[0]
web_weibo_url = "http://weibo.com/%s/profile?topnav=1&wvr=6&is_all=1" % uuid_res
weibo_page = self.session.get(web_weibo_url, headers=headers) # print(weibo_page.content.decode("utf-8") Mheaders = {
"Host": "login.sina.com.cn",
"User-Agent": agent
} # m.weibo.cn 登录的 url 拼接
_rand = str(time.time())
mParams = {
"url": "https://m.weibo.cn/",
"_rand": _rand,
"gateway": "",
"service": "sinawap",
"entry": "sinawap",
"useticket": "",
"returntype": "META",
"sudaref": "",
"_client_version": "0.6.26",
}
murl = "https://login.sina.com.cn/sso/login.php"
mhtml = self.session.get(murl, params=mParams, headers=Mheaders)
mhtml.encoding = mhtml.apparent_encoding
mpa = r'replace\((.*?)\);'
mres = re.findall(mpa, mhtml.text) # 关键的跳转步骤，这里不出问题，基本就成功了。
Mheaders["Host"] = "passport.weibo.cn"
self.session.get(eval(mres[0]), headers=Mheaders)
mlogin = self.session.get(eval(mres[0]), headers=Mheaders)
# print(mlogin.status_code)
# 进过几次 页面跳转后，m.weibo.cn 登录成功，下次测试是否登录成功
Mheaders["Host"] = "m.weibo.cn"
Set_url = "https://m.weibo.cn"
pro = self.session.get(Set_url, headers=Mheaders)
pa_login = r'isLogin":true,'
login_res = re.findall(pa_login, pro.text)
# print(login_res) # 可以通过 session.cookies 对 cookies 进行下一步相关操作
self.session.cookies.save()
# print("*"*50)
# print(self.cookie_path)
第五步：定义cookie的加载和信息的重定义
def get_cookies():
# 加载cookie
cookies = cookielib.LWPCookieJar("Cookie.txt")
cookies.load(ignore_discard=True, ignore_expires=True)
# 将cookie转换成字典
cookie_dict = requests.utils.dict_from_cookiejar(cookies)
return cookie_dict def info_parser(data):
id,time,text = data['id'],data['created_at'],data['text']
user = data['user']
uid,username,following,followed,gender = \
user['id'],user['screen_name'],user['follow_count'],user['followers_count'],user['gender']
return {
'wid':id,
'time':time,
'text':text,
'uid':uid,
'username':username,
'following':following,
'followed':followed,
'gender':gender
}
第六步：开始爬
def start_crawl(cookie_dict,id):
base_url = 'https://m.weibo.cn/comments/hotflow?id={}&mid={}&max_id_type=0'
next_url = 'https://m.weibo.cn/comments/hotflow?id={}&mid={}&max_id={}&max_id_type={}'
page = 1
id_type = 0
comment_count = 0
requests_count = 1
res = requests.get(url=base_url.format(id,id), headers=headers,cookies=cookie_dict)
while True:
print('parse page {}'.format(page))
page += 1
try:
data = res.json()['data']
wdata = []
max_id = data['max_id']
for c in data['data']:
comment_count += 1
row = info_parser(c)
wdata.append(info_parser(c))
if c.get('comments', None):
temp = []
for cc in c.get('comments'):
temp.append(info_parser(cc))
wdata.append(info_parser(cc))
comment_count += 1
row['comments'] = temp
print(row)
with open('{}/{}.csv'.format(comment_path, id), mode='a+', encoding='utf-8-sig', newline='') as f:
writer = csv.writer(f)
for d in wdata:
writer.writerow([d['wid'],d['time'],d['text'],d['uid'],d['username'],d['following'],d['followed'],d['gender']]) time.sleep(3)
except:
print(res.text)
id_type += 1
print('评论总数: {}'.format(comment_count)) res = requests.get(url=next_url.format(id, id, max_id,id_type), headers=headers,cookies=cookie_dict)
requests_count += 1
if requests_count%50==0:
print(id_type)
print(res.status_code)
第七步：主函数
if __name__ == '__main__':
username = "" # 用户名（注册的手机号）
password = "" # 密码
cookie_path = "Cookie.txt" # 保存cookie 的文件名称
id = '' # 爬取微博的 id
WeiboLogin(username, password, cookie_path).login()
with open('{}/{}.csv'.format(comment_path, id), mode='w', encoding='utf-8-sig', newline='') as f:
writer = csv.writer(f)
writer.writerow(['wid', 'time', 'text', 'uid', 'username', 'following', 'followed', 'gender'])
start_crawl(get_cookies(), id)
第八步：获取id
- 你需要获得想要找的微博id，那么对于小白来说怎么找id呢？
- 首先找到你想爬的微博，这里以微博故事为例，在浏览器内按下F12，并且点击评论按钮
- 点击‘网络’，找到一条像图中的get请求。查看它的参数，mid就是它的id
全文代码
为了方便大家拿去练习，以下是上文的全部代码整合！
import time
import base64
import rsa
import binascii
import requests
import re
from PIL import Image
import random
from urllib.parse import quote_plus
import http.cookiejar as cookielib
import csv
import os
comment_path = 'comment'
if not os.path.exists(comment_path):
os.mkdir(comment_path) agent = 'mozilla/5.0 (windowS NT 10.0; win64; x64) appLewEbkit/537.36 (KHTML, likE gecko) chrome/71.0.3578.98 safari/537.36'
headers = {'User-Agent': agent} class WeiboLogin(object):
"""
通过登录 weibo.com 然后跳转到 m.weibo.cn
""" # 初始化数据
def __init__(self, user, password, cookie_path):
super(WeiboLogin, self).__init__()
self.user = user
self.password = password
self.session = requests.Session()
self.cookie_path = cookie_path
# LWPCookieJar是python中管理cookie的工具，可以将cookie保存到文件，或者在文件中读取cookie数据到程序
self.session.cookies = cookielib.LWPCookieJar(filename=self.cookie_path)
self.index_url = "http://weibo.com/login.php"
self.session.get(self.index_url, headers=headers, timeout=2)
self.postdata = dict() def get_su(self):
"""
对 email 地址和手机号码 先 javascript 中 encodeURIComponent
对应 Python 3 中的是 urllib.parse.quote_plus
然后在 base64 加密后decode
"""
username_quote = quote_plus(self.user)
username_base64 = base64.b64encode(username_quote.encode("utf-8"))
return username_base64.decode("utf-8") # 预登陆获得 servertime, nonce, pubkey, rsakv
def get_server_data(self, su):
"""与原来的相比，微博的登录从 v1.4.18 升级到了 v1.4.19
这里使用了 URL 拼接的方式，也可以用 Params 参数传递的方式
"""
pre_url = "http://login.sina.com.cn/sso/prelogin.php?entry=weibo&callback=sinaSSOController.preloginCallBack&su="
pre_url = pre_url + su + "&rsakt=mod&checkpin=1&client=ssologin.js(v1.4.19)&_="
pre_url = pre_url + str(int(time.time() * 1000))
pre_data_res = self.session.get(pre_url, headers=headers)
# print("*"*50)
# print(pre_data_res.text)
# print("*" * 50)
sever_data = eval(pre_data_res.content.decode("utf-8").replace("sinaSSOController.preloginCallBack", '')) return sever_data def get_password(self, servertime, nonce, pubkey):
"""对密码进行 RSA 的加密"""
rsaPublickey = int(pubkey, 16)
key = rsa.PublicKey(rsaPublickey, 65537) # 创建公钥
message = str(servertime) + '\t' + str(nonce) + '\n' + str(self.password) # 拼接明文js加密文件中得到
message = message.encode("utf-8")
passwd = rsa.encrypt(message, key) # 加密
passwd = binascii.b2a_hex(passwd) # 将加密信息转换为16进制。
return passwd def get_cha(self, pcid):
"""获取验证码，并且用PIL打开，
1. 如果本机安装了图片查看软件，也可以用 os.subprocess 的打开验证码
2. 可以改写此函数接入打码平台。
"""
cha_url = "https://login.sina.com.cn/cgi/pin.php?r="
cha_url = cha_url + str(int(random.random() * 100000000)) + "&s=0&p="
cha_url = cha_url + pcid
cha_page = self.session.get(cha_url, headers=headers)
with open("cha.jpg", 'wb') as f:
f.write(cha_page.content)
f.close()
try:
im = Image.open("cha.jpg")
im.show()
im.close()
except Exception as e:
print(u"请到当前目录下，找到验证码后输入") def pre_login(self):
# su 是加密后的用户名
su = self.get_su()
sever_data = self.get_server_data(su)
servertime = sever_data["servertime"]
nonce = sever_data['nonce']
rsakv = sever_data["rsakv"]
pubkey = sever_data["pubkey"]
showpin = sever_data["showpin"] # 这个参数的意义待探索
password_secret = self.get_password(servertime, nonce, pubkey) self.postdata = {
'entry': 'weibo',
'gateway': '',
'from': '',
'savestate': '',
'useticket': '',
'pagerefer': "https://passport.weibo.com",
'vsnf': '',
'su': su,
'service': 'miniblog',
'servertime': servertime,
'nonce': nonce,
'pwencode': 'rsa2',
'rsakv': rsakv,
'sp': password_secret,
'sr': '1366*768',
'encoding': 'UTF-8',
'prelt': '',
"cdult": "",
'url': 'http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack',
'returntype': 'TEXT' # 这里是 TEXT 和 META 选择，具体含义待探索
}
return sever_data def login(self):
# 先不输入验证码登录测试
try:
sever_data = self.pre_login()
login_url = 'https://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)&_'
login_url = login_url + str(time.time() * 1000)
login_page = self.session.post(login_url, data=self.postdata, headers=headers)
ticket_js = login_page.json()
ticket = ticket_js["ticket"]
except Exception as e:
sever_data = self.pre_login()
login_url = 'https://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)&_'
login_url = login_url + str(time.time() * 1000)
pcid = sever_data["pcid"]
self.get_cha(pcid)
self.postdata['door'] = input(u"请输入验证码")
login_page = self.session.post(login_url, data=self.postdata, headers=headers)
ticket_js = login_page.json()
ticket = ticket_js["ticket"]
# 以下内容是 处理登录跳转链接
save_pa = r'==-(\d+)-'
ssosavestate = int(re.findall(save_pa, ticket)[0]) + 3600 * 7
jump_ticket_params = {
"callback": "sinaSSOController.callbackLoginStatus",
"ticket": ticket,
"ssosavestate": str(ssosavestate),
"client": "ssologin.js(v1.4.19)",
"_": str(time.time() * 1000),
}
jump_url = "https://passport.weibo.com/wbsso/login"
jump_headers = {
"Host": "passport.weibo.com",
"Referer": "https://weibo.com/",
"User-Agent": headers["User-Agent"]
}
jump_login = self.session.get(jump_url, params=jump_ticket_params, headers=jump_headers)
uuid = jump_login.text uuid_pa = r'"uniqueid":"(.*?)"'
uuid_res = re.findall(uuid_pa, uuid, re.S)[0]
web_weibo_url = "http://weibo.com/%s/profile?topnav=1&wvr=6&is_all=1" % uuid_res
weibo_page = self.session.get(web_weibo_url, headers=headers) # print(weibo_page.content.decode("utf-8") Mheaders = {
"Host": "login.sina.com.cn",
"User-Agent": agent
} # m.weibo.cn 登录的 url 拼接
_rand = str(time.time())
mParams = {
"url": "https://m.weibo.cn/",
"_rand": _rand,
"gateway": "",
"service": "sinawap",
"entry": "sinawap",
"useticket": "",
"returntype": "META",
"sudaref": "",
"_client_version": "0.6.26",
}
murl = "https://login.sina.com.cn/sso/login.php"
mhtml = self.session.get(murl, params=mParams, headers=Mheaders)
mhtml.encoding = mhtml.apparent_encoding
mpa = r'replace\((.*?)\);'
mres = re.findall(mpa, mhtml.text) # 关键的跳转步骤，这里不出问题，基本就成功了。
Mheaders["Host"] = "passport.weibo.cn"
self.session.get(eval(mres[0]), headers=Mheaders)
mlogin = self.session.get(eval(mres[0]), headers=Mheaders)
# print(mlogin.status_code)
# 进过几次 页面跳转后，m.weibo.cn 登录成功，下次测试是否登录成功
Mheaders["Host"] = "m.weibo.cn"
Set_url = "https://m.weibo.cn"
pro = self.session.get(Set_url, headers=Mheaders)
pa_login = r'isLogin":true,'
login_res = re.findall(pa_login, pro.text)
# print(login_res) # 可以通过 session.cookies 对 cookies 进行下一步相关操作
self.session.cookies.save()
# print("*"*50)
# print(self.cookie_path) def get_cookies():
# 加载cookie
cookies = cookielib.LWPCookieJar("Cookie.txt")
cookies.load(ignore_discard=True, ignore_expires=True)
# 将cookie转换成字典
cookie_dict = requests.utils.dict_from_cookiejar(cookies)
return cookie_dict def info_parser(data):
id,time,text = data['id'],data['created_at'],data['text']
user = data['user']
uid,username,following,followed,gender = \
user['id'],user['screen_name'],user['follow_count'],user['followers_count'],user['gender']
return {
'wid':id,
'time':time,
'text':text,
'uid':uid,
'username':username,
'following':following,
'followed':followed,
'gender':gender
} def start_crawl(cookie_dict,id):
base_url = 'https://m.weibo.cn/comments/hotflow?id={}&mid={}&max_id_type=0'
next_url = 'https://m.weibo.cn/comments/hotflow?id={}&mid={}&max_id={}&max_id_type={}'
page = 1
id_type = 0
comment_count = 0
requests_count = 1
res = requests.get(url=base_url.format(id,id), headers=headers,cookies=cookie_dict)
while True:
print('parse page {}'.format(page))
page += 1
try:
data = res.json()['data']
wdata = []
max_id = data['max_id']
for c in data['data']:
comment_count += 1
row = info_parser(c)
wdata.append(info_parser(c))
if c.get('comments', None):
temp = []
for cc in c.get('comments'):
temp.append(info_parser(cc))
wdata.append(info_parser(cc))
comment_count += 1
row['comments'] = temp
print(row)
with open('{}/{}.csv'.format(comment_path, id), mode='a+', encoding='utf-8-sig', newline='') as f:
writer = csv.writer(f)
for d in wdata:
writer.writerow([d['wid'],d['time'],d['text'],d['uid'],d['username'],d['following'],d['followed'],d['gender']]) time.sleep(3)
except:
print(res.text)
id_type += 1
print('评论总数: {}'.format(comment_count)) res = requests.get(url=next_url.format(id, id, max_id,id_type), headers=headers,cookies=cookie_dict)
requests_count += 1
if requests_count%50==0:
print(id_type)
print(res.status_code) if __name__ == '__main__':
username ="" # 用户名（注册的手机号）
password = "" # 密码
cookie_path = "Cookie.txt" # 保存cookie 的文件名称
id = '' # 爬取微博的 id
WeiboLogin(username, password, cookie_path).login()
with open('{}/{}.csv'.format(comment_path, id), mode='w', encoding='utf-8-sig', newline='') as f:
writer = csv.writer(f)
writer.writerow(['wid', 'time', 'text', 'uid', 'username', 'following', 'followed', 'gender'])
start_crawl(get_cookies(), id)
Python爬虫抓取微博评论的更多相关文章
- 一篇文章教会你使用Python定时抓取微博评论
[Part1--理论篇] 试想一个问题,如果我们要抓取某个微博大V微博的评论数据,应该怎么实现呢?最简单的做法就是找到微博评论数据接口,然后通过改变参数来获取最新数据并保存.首先从微博api寻找抓取评 ...
- python 爬虫抓取心得
quanwei9958 转自 python 爬虫抓取心得分享 urllib.quote('要编码的字符串') 如果你要在url请求里面放入中文,对相应的中文进行编码的话,可以用: urllib.quo ...
- Python爬虫----抓取豆瓣电影Top250
有了上次利用python爬虫抓取糗事百科的经验,这次自己动手写了个爬虫抓取豆瓣电影Top250的简要信息. 1.观察url 首先观察一下网址的结构 http://movie.douban.com/to ...
- Python爬虫抓取东方财富网股票数据并实现MySQL数据库存储
Python爬虫可以说是好玩又好用了.现想利用Python爬取网页股票数据保存到本地csv数据文件中,同时想把股票数据保存到MySQL数据库中.需求有了,剩下的就是实现了. 在开始之前,保证已经安装好 ...
- python爬虫抓取哈尔滨天气信息（静态爬虫）
python 爬虫 爬取哈尔滨天气信息 - http://www.weather.com.cn/weather/101050101.shtml 环境: windows7 python3.4(pip i ...
- 用python+selenium抓取微博24小时热门话题的前15个并保存到txt中
抓取微博24小时热门话题的前15个,抓取的内容请保存至txt文件中,需要抓取排行.话题和阅读数 #coding=utf-8 from selenium import webdriver import ...
- Python抓取微博评论(二)
对于新浪微博评论的抓取,首篇做的时候有些考虑不周,然后现在改正了一些地方,因为有人问,抓取评论的时候“爬前50页的热评,或者最新评论里的前100页“,这样的数据看了看,好像每条微博的评论都只能抓取到前 ...
- Python抓取微博评论
本人是张杰的小迷妹,所以用杰哥的微博为例,之前一直看的是网页版,然后在知乎上看了一个抓取沈梦辰的微博评论的帖子,然后得到了这样的网址 然后就用m.weibo.cn进行网站的爬取,里面的微博和每一条微博 ...
- 如何科学地蹭热点：用python爬虫获取热门微博评论并进行情感分析
前言:本文主要涉及知识点包括新浪微博爬虫.python对数据库的简单读写.简单的列表数据去重.简单的自然语言处理(snowNLP模块.机器学习).适合有一定编程基础,并对python有所了解的盆友阅读 ...
随机推荐
- 吴裕雄--天生自然C语言开发：位域
struct { unsigned int widthValidated; unsigned int heightValidated; } status; struct { unsigned ; un ...
- Linux 杀死进程方法大全(kill,killall)
杀死进程最安全的方法是单纯使用kill命令,不加修饰符,不带标志. 首先使用ps -ef命令确定要杀死进程的PID,然后输入以下命令: # kill -pid 注释:标准的kill命令通常 ...
- Java面试题2-附答案
JVM的内存结构 根据 JVM 规范,JVM 内存共分为虚拟机栈.堆.方法区.程序计数器.本地方法栈五个部分. 1.Java虚拟机栈: 线程私有:每个方法在执行的时候会创建一个栈帧,存储了局部变量表, ...
- EXAM-2018-7-29
EXAM-2018-7-29 未完成 [ ] H [ ] A D 莫名TLE 不在循环里写strlen()就行了 F 相减特判 水题 J 模拟一下就可以发现规律,o(n) K 每个数加一减一不变,用m ...
- django框架中的cookie与session
cookie因为http是一个无状态协议,无法记录用户上一步的操作,所以需要状态保持.cookie和session的区别:1.cookie是保存在浏览器本地的,所以相对不安全.cookie是4k的大小 ...
- deeplearning.ai 构建机器学习项目 Week 1 机器学习策略 I
这门课是讲一些分析机器学习问题的方法,如何更快速高效的优化机器学习系统,以及NG自己的工程经验和教训. 1. 正交化(Othogonalization) 设计机器学习系统时需要面对一个问题是:可以尝试 ...
- linux centos的安装及一些相关知识的整理
相关知识点 ***网桥:主机和虚拟机之间使用"桥接"网络组网 VMware 0 ***Net适配器:把本地网中虚拟机的ip地址转换为主机的外部网络地址 ***仅主机适 ...
- python2查找匹配数据及类型转换
判断一个字符是否包含在另一个字符串中,如果包含,但是数据类型不同,需要进行数据类型转换 下面这个是针对python2
- OpenCV 输入输出XML和YAML文件
#include <opencv2/core/core.hpp> #include <iostream> #include <string> using names ...
- 深入 Java 调试体系: 第 1 部分，JPDA 体系概览
JPDA 概述 所有的程序员都会遇到 bug,对于运行态的错误,我们往往需要一些方法来观察和测试运行态中的环境.在 Java 程序中,最简单的,您是否尝试过使用 System.out.println( ...