一. 要求:
①、输入贴吧名称:正能量吧
②、输入起始页:1
③、输入终止页:3
④、保存到本地文件
正能量吧-第1页.html、赵丽颖吧-第2页.html
二. 实现步骤:
1. 查看是否为静态页面
右键 -> 查看网页源代码 -> 搜索数据关键字
2. 找到URL规律
第一页: http://tieba.baidu.com/f?kw=??&pn=0
第二页: http://tieba.baidu.com/f?kw=??&pn=50
第 n 页: pn = (n-1) * 50
3. 获取网页内容
4. 提取所需数据
5. 保存(本地文件,数据库)
from urllib import request, parse
import random
import time
class TiebaSpider(object):
def __init__(self):
self.url = "https://tieba.baidu.com/f?kw={}&pn={}"
self.headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'}
# 获取响应内容
def get_page(self, url):
req = request.Request(url=url, headers=self.headers)
res = request.urlopen(req)
html = res.read().decode()
return html
# 解析,提取数据
def parse_page(self):
pass
# 保存数据
def write_page(self, filename, html):
with open(filename, 'w', encoding='utf-8') as f:
f.write(html)
# 入口函数
def run(self):
name = input("请输入贴吧名:")
start = int(input('请输入起始页:'))
end = int(input('请输入终止页:'))
kw = parse.quote(name)
# 拼接 + 获取内容 + 保存
for i in range(start, end + 1):
pn = (i - 1) * 50
url = self.url.format(kw, pn)
html = self.get_page(url)
filename = '{}-第{}页.html'.format(name, i)
self.write_page(filename, html)
print('第%d页抓取成功' % i)
# 每爬1一个页面随机休眠1-3秒
time.sleep(random.randint(1, 3))
if __name__ == '__main__':
begin = time.time()
spider = TiebaSpider()
spider.run()
stop = time.time()
print('执行时间:%.2f' % (stop - begin))
三. 案例优化
两种方式:
1. 将User-Agent提取成单个文件
因为同一个User-Agent大量访问同一个地址也会被判定为爬虫
(1). userAgent.py
ua_list = [
"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",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
"Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
"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",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv,2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; rv,2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
"MAC:Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36",
"Windows:Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"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",
"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",
"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",
"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",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"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",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
"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",
"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)"
"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)",
"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)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
"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",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"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",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4094.1 Safari/537.36",
"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",
"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",
"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",
"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",
"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",
"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
"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",
"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
"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",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
"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",
"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",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
"UCWEB7.0.2.37/28/999",
"NOKIA5700/ UCWEB7.0.2.37/28/999",
"Openwave/ UCWEB7.0.2.37/28/999",
"Openwave/ UCWEB7.0.2.37/28/999",
]
(2). demo.py
from urllib import request, parse
import random
import time
from userAgent import ua_list # 导入user-agent
class TiebaSpider(object):
def __init__(self):
self.url = "https://tieba.baidu.com/f?kw={}&pn={}"
# 获取响应内容
def get_page(self, url):
# 随机提取user-Agent
headers = {'User-Agent': random.choice(ua_list)}
req = request.Request(url=url, headers=headers)
res = request.urlopen(req)
html = res.read().decode()
return html
...
2. 使用 fake_useragent模块
(1) . 安装模块
# 通过模块获取User-Agent
pip install fake_useragent
(2). 使用模块
from fake_useragent import UserAgent
ua = UserAgent() # 获取对象
print(ua.random)
(3). 代码中使用模块
...
from fake_useragent import UserAgent
class TiebaSpider(object):
def __init__(self):
self.url = "https://tieba.baidu.com/f?kw={}&pn={}"
# 生成随机的User-Agent
def get_headers(self):
ua = UserAgent() # 获取对象
headers = {'User-Agent': ua.random}
print(headers)
return headers
# 获取响应内容
def get_page(self, url):
# 随机提取user-Agent
headers = self.get_headers()
...
...
四. 正则解析模块
1. re模块使用流程
方法一:
r_list = re.findall('正则表达式',html,re.S) #re.S:允许 . 匹配/n
方法二:
# 1. 创建正则编译对象
pattern = re.compile(r'正则表达式',re.S)
r_list=pattern.findall(html)
2. 正则表达式元字符
3. 贪婪模式和非贪婪模式
import re
html = """
<div><p>窗前明月光</p></div>
<div><p>疑是地上霜</p></div>
"""
# 贪婪匹配
pattern = re.compile('<div><p>.*</p></div>', re.S)
r_list = pattern.findall(html)
# 非贪婪模式(使用最多)
pattern = re.compile('<div><p>.*?</p></div>', re.S)
r_list = pattern.findall(html)
print(r_list)
4. 正则表达式分组
作用: 在完整的模式中定义子模式,将每个圆括号中子模式匹配出来的结果提取出来
import re
s = 'A B C D'
p1 = re.compile('\w+\s+\w+')
print(p1.findall(s)) # ['A B', 'C D']
p2 = re.compile('(\w+)\s+\w+')
# 第一步: 匹配完整 -> ['A B', 'C D']
# 第二步: 匹配()中 -> ['A', 'C']
print(p2.findall(s))
p3 = re.compile('(\w+)\s+(\w+)')
# 第一步: 匹配完整 -> ['A B', 'C D']
# 第二步: 匹配()中 -> [('A', 'B'), ('C', 'D')]
print(p3.findall(s))
分组总结:
1、在网页中,想要什么内容,就加()
2、多个分组先按整体正则匹配,然后再提取()中数据。结果:[(),(),()]
五.总结
(1)、确定所抓取数据在响应中是否存在(右键 查看网页源码-搜索关键字)l
(2)、数据存在: 查看URL地址规律
(3)、写正则表达式,来匹配数据
(4)、程序结构
①、使用随机User-Agent
②、每爬取1个页面后随机休眠一段时间