|
这个是“关键词”爬取，如果mysql数据库不会改，建议把mysql有关的代码注释或删除。
注意，时间为我自己添加上去的，如果时间跨度较长，百度指数时间会变为一个星期一次数据，而我添加的为每天，需自己更改。
有时候访问有问题，可以等一段时间在试，不知道为什么有时候可以访问，有时候不行。
cookie需自行添加
代码如下：
# -*- coding: utf-8 -*-
# @Time : 2021/9/4 21:55
# @Author : luoye
# @FileName: 关键词.py
# @Software: PyCharm
import random
import time
import requests
import execjs
from datetime import datetime, timedelta
import pandas as pd
import pymysql
def getheaders():
# 各种PC端
user_agent_list_2 = [
# Opera
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60",
"Opera/8.0 (Windows NT 5.1; U; en)",
"Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50",
# Firefox
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0",
"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
# Safari
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
# chrome
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
# 360
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
# 淘宝浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
# 猎豹浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
# QQ浏览器
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
# sogou浏览器
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0)",
# maxthon浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36",
# UC浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 UBrowser/4.0.3214.0 Safari/537.36",
]
# 各种移动端
user_agent_list_3 = [
# IPhone
"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
# IPod
"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
# IPAD
"Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
# Android
"Mozilla/5.0 (Linux; U; Android 2.2.1; zh-cn; HTC_Wildfire_A3333 Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
# QQ浏览器 Android版本
"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
# Android Opera Mobile
"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
# Android Pad Moto Xoom
"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
# BlackBerry
"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
# WebOS HP Touchpad
"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
# Nokia N97
"Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
# Windows Phone Mango
"Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
# UC浏览器
"UCWEB7.0.2.37/28/999",
"NOKIA5700/ UCWEB7.0.2.37/28/999",
# UCOpenwave
"Openwave/ UCWEB7.0.2.37/28/999",
# UC Opera
"Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999"
]
# 一部分 PC端的
user_agent_list_1 = [
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
"Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
]
user_agent_list = user_agent_list_1 + user_agent_list_2 + user_agent_list_3
UserAgent = random.choice(user_agent_list)
return UserAgent
class BaiDuZhiShu():
def __init__(self, table):
self.headers = {
'Cookie': 'your cookie',
'Host': 'index.baidu.com',
'Referer': 'https://index.baidu.com/v2/main/index.html',
'User-Agent': getheaders(),
}
self.table = table
self.i = 1
self.df = None
self.conn = pymysql.connect(host='127.0.0.1', user='root', password="your password", database='baidu',
charset='utf8')
# 从当前日期到结束日期的天列表
def get_time_days(self, start, end):
days_list = []
start = datetime.strptime(start, '%Y-%m-%d')
end = datetime.strptime(end, '%Y-%m-%d')
while start <= end:
days_list.append(start.strftime('%Y-%m-%d'))
start += timedelta(days=1)
return days_list
def decrypt(self, t, e):
js_decrypt = '''
function decrypt(t, e) {
if (t) {
for (var n = t.split(""), i = e.split(""), a = {}, r = [], o = 0; o < n.length / 2; o++)
a[n[o]] = n[n.length / 2 + o];
for (var s = 0; s < e.length; s++)
r.push(a[i[s]]);
return r.join("")
}
}
'''
compile = execjs.compile(js_decrypt)
data = compile.call('decrypt', t, e)
list_1 = []
for i in data.split(','):
if i:
list_1.append(int(i))
else:
list_1.append(int(0))
return list_1
def get_t(self, uniqid):
url = f'https://index.baidu.com/Interface/ptbk?uniqid={uniqid}'
return requests.get(url, headers=self.headers).json()['data']
def get_csv(self, name, decrypt_data, days_list):
# name 为列名
if len(decrypt_data) == len(days_list):
list_data = [{"time": days_list[i], name: decrypt_data[i]} for i in range(len(days_list))]
list_1 = []
list_2 = []
for i in list_data:
list_1.append(i['time'])
list_2.append(i[name])
# self.get_shuju(name, pd.DataFrame({'time': list_1, name: list_2}))
# self.df.to_csv('./百度热搜电影榜.csv')
# 更新数据
self.update(name, days_list, list_2)
return pd.DataFrame({'time': list_1, name: list_2})
def run(self, name, start_day, end_day):
'''
:start_day:开始时间，例如2020-09-03
:end_day:结束时间，例如2021-09-03
'''
days_list = self.get_time_days(start_day, end_day)
# 是否有表
self.is_table()
# 表中是否有改列的数据
with self.conn.cursor() as cur:
cur.execute(f"SELECT COLUMN_NAME FROM information_schema.COLUMNS WHERE table_name = '{self.table}';")
baiti_list = [i[0] for i in cur.fetchall()]
if name in baiti_list:
return None
# {}花括号转移为两个花括号
url = f'https://index.baidu.com/api/SearchApi/index?area=0&word=[[{{"name":"{name}","wordType":1}}]]&startDate={start_day}&endDate={end_day}'
page = requests.get(url, headers=self.headers).json()
uniqid = page['data']['uniqid']
t = self.get_t(uniqid)
e = page['data']['userIndexes'][0]['all']['data']
decrypt_data = self.decrypt(t, e)
dataframe = self.get_csv(name, decrypt_data, days_list)
self.get_shuju(name, dataframe)
def get_shuju(self, name, dataframe):
if self.i == 1:
self.df = dataframe
self.i += 1
else:
self.df[name] = dataframe[name]
# 判断是否有表
def is_table(self):
if not self.table.split(',')[-1] == time.strftime("%Y-%m-%d", time.localtime()):
self.table = self.table.split(',')[0] + f',{time.strftime("%Y-%m-%d", time.localtime())}'
with self.conn.cursor() as cur:
# 判断是否有表
if not cur.execute(f"show tables like '{self.table}';"):
# 创建只有time列的表
cur.execute(
f'CREATE TABLE `baidu`.`{self.table}`( `time` VARCHAR(20) NOT NULL, PRIMARY KEY (`time`) ) CHARSET=utf8')
# 更新数据
def update(self, name, days_list, list_data):
with self.conn.cursor() as cur:
cur.execute(f'SELECT time FROM `{self.table}`;')
list_tuple = cur.fetchall()
if not list_tuple:
for time in days_list:
# 把所有时间写入主键time
cur.execute(f"INSERT INTO `baidu`.`{self.table}` (`time`) VALUES ('{time}'); ")
self.conn.commit() # 提交数据
# 获取表的列
cur.execute(f"SELECT COLUMN_NAME FROM information_schema.COLUMNS WHERE table_name = '{self.table}';")
baiti_list = [i[0] for i in cur.fetchall()]
if name not in baiti_list:
# 添加列
cur.execute(f'ALTER TABLE `baidu`.`{self.table}` ADD COLUMN `{name}` INT NULL AFTER `time`;')
self.conn.commit()
for i in range(len(days_list)):
cur.execute(
f"UPDATE `baidu`.`{self.table}` SET `{name}` = '{list_data[i]}' WHERE `time` = '{days_list[i]}';")
self.conn.commit()
if __name__ == '__main__':
bd = BaiDuZhiShu('百度电视剧榜')
for name in ['你好']:
bd.run(name, '2021-08-01', '2021-09-17')
# 保存为csv格式
bd.df.to_csv(f'./{bd.table}.csv')
print(bd.df)
下面是百度指数 娱乐人物
这个也需要cookie，需自行添加，分析方式与上面基本相同，代码也可以一样，不过有时候百度指数容易抽风，于是写了数据库。
# -*- coding: utf-8 -*-
# @Time : 2021/9/18 20:05
# @Author : luoye
# @FileName: 百度指数_娱乐.py
# @Software: PyCharm
import random
import execjs
from datetime import datetime, timedelta
import requests
import pandas as pd
class YuLe():
def __init__(self, table, cookies):
self.headers = {
'Cookie': cookies,
'Host': 'index.baidu.com',
'Referer': 'https://index.baidu.com/v2/main/index.html',
'User-Agent': self.getheaders(),
}
self.dict_data = {}
self.table = table
def getheaders(self):
# 各种PC端
user_agent_list_2 = [
# Opera
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60",
"Opera/8.0 (Windows NT 5.1; U; en)",
"Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50",
# Firefox
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0",
"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
# Safari
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
# chrome
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
# 360
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
# 淘宝浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
# 猎豹浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
# QQ浏览器
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
# sogou浏览器
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0)",
# maxthon浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36",
# UC浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 UBrowser/4.0.3214.0 Safari/537.36",
]
# 各种移动端
user_agent_list_3 = [
# IPhone
"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
# IPod
"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
# IPAD
"Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
# Android
"Mozilla/5.0 (Linux; U; Android 2.2.1; zh-cn; HTC_Wildfire_A3333 Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
# QQ浏览器 Android版本
"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
# Android Opera Mobile
"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
# Android Pad Moto Xoom
"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
# BlackBerry
"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
# WebOS HP Touchpad
"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
# Nokia N97
"Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
# Windows Phone Mango
"Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
# UC浏览器
"UCWEB7.0.2.37/28/999",
"NOKIA5700/ UCWEB7.0.2.37/28/999",
# UCOpenwave
"Openwave/ UCWEB7.0.2.37/28/999",
# UC Opera
"Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999"
]
# 一部分 PC端的
user_agent_list_1 = [
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
"Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
]
user_agent_list = user_agent_list_1 + user_agent_list_2 + user_agent_list_3
UserAgent = random.choice(user_agent_list)
return UserAgent
# 从当前日期到结束日期的天列表
def get_time_days(self, start, end):
days_list = []
start = datetime.strptime(start, '%Y%m%d')
end = datetime.strptime(end, '%Y%m%d')
while start <= end:
days_list.append(start.strftime('%Y-%m-%d'))
start += timedelta(days=1)
return days_list
def get_nodeid(self, name):
url = f'https://index.baidu.com/api/SugApi/sug?inputword[]={name}&ischeckType=15'
page = requests.get(url, headers=self.headers).json()
id = page['data']['wordlist'][0]['id']
return id
# 获取
def get_uniqid_all(self, nodeid):
url = f'https://index.baidu.com/Interface/Newwordgraph/getTopicFeed?nodeid={nodeid}'
page = requests.get(url, headers=self.headers).json()
e = page['data']['index']['_all']
time_list = page['data']['index']['period'].split('|')
uniqid = page['uniqid']
return [e, uniqid, time_list]
# 获取t
def get_t(self, uniqid):
url = f'https://index.baidu.com/Interface/api/ptbkTopic?uniqid={uniqid}'
page = requests.get(url, headers=self.headers).json()
data = page['data']
# "jqw,WVhk1K-98QB7+824.69-%013,5"
return data
# 解密
def decrypt(self, t, e):
js_decrypt = '''
function decrypt(t, e) {
if (t) {
for (var n = t.split(""), i = e.split(""), a = {}, r = [], o = 0; o < n.length / 2; o++)
a[n[o]] = n[n.length / 2 + o];
for (var s = 0; s < e.length; s++)
r.push(a[i[s]]);
return r.join("")
}
}
'''
compile = execjs.compile(js_decrypt)
data = compile.call('decrypt', t, e)
list_1 = []
for i in data.split(','):
if i:
list_1.append(int(i))
else:
list_1.append(int(0))
return list_1
# 保存
def save_csv(self):
pd.DataFrame(self.dict_data).to_csv(f'./{self.table}.csv')
# 启动
def run(self, name):
nodeid = self.get_nodeid(name)
e, uniqid, time_list = self.get_uniqid_all(nodeid)
if 'time' not in self.dict_data.keys():
self.dict_data['time'] = self.get_time_days(*time_list)
t = self.get_t(uniqid)
list_1 = self.decrypt(t, e)
print(list_1)
self.dict_data[name] = list_1
if __name__ == '__main__':
# 查找的是 娱乐人物
# 百度指数只能看一个月
# 添加cookies
cookies = 'your cookie'
# 保存的名字为 电视剧
yule = YuLe('电视剧', cookies=cookies)
# 此为扫黑风暴演员表
for name in ['孙红雷', '张艺兴', '刘奕君', '吴越', '江疏影', '王志飞', '刘之冰', '吴晓亮', '宁理', '车晓', '苏可', '谭凯', '姜寒', '侯长荣', '赵立根',
'孙浩', '周晓鸥', '王骏迪', '周知', '赵小锐', '郑晓宁', '姜瑞佳', '葛四', '孙筱钧', '齐超', '李飞', '魏子昕', '郭秋成', '张弓', '文予琪',
'刘扬', '王妍之', '张皓然', '杨雨潼', '张浩天', '刘柠昊', '单思杰', '陈芷琰', '曹艳艳', '杨奇雨', '田璐', '成止微', '项洪', '李先亮', '常诚',
'栾茗媛', '丁志勇', '张继南', '朱怀旭', '付枚', '曹阳']:
try:
yule.run(name)
except:
# 娱乐板块搜不到
pass
# 保存为csv格式
yule.save_csv()
|