自学PYTHON爬虫笔记

weixin_47932683

已于 2022-03-31 11:47:52 修改

阅读量1.5k

点赞数 1

文章标签： python

于 2022-03-30 18:26:36 首次发布

本文链接：https://blog.csdn.net/weixin_47932683/article/details/123853444

版权

自学PYTHON爬虫笔记

一、Reqest库的安装（Pycharm）

#https://pypi.douban.com/simple/
#https://pypi.tuna.tsinghua.edu.cn/simple/
#镜像网址
第一步：
1、打开File-Setting—项目名称-Python Interpreter
2、点击加号-输入需要安装的库名（Request）
3、如果下载缓慢可以点击（Manage Repositories）-点击加号，输入镜像网址

二、实操(百度案例——简单请求)

import requests
url='http://www.baidu.com/'
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.82 Safari/537.36',
'Cookie':'BAIDUID_BFESS=3D81F763FDCAF5D6E4FB1604872E3F67:FG=1; BIDUPSID=163E11FA986B4424651C65E6A98C0C88; PSTM=1648540356; BAIDUID=163E11FA986B44244762FDE6F138C1AF:FG=1; BD_HOME=1; H_PS_PSSID=36159_36176_31254_35909_36166_34584_36144_36120_36194_35801_35321_26350_35724_36101_36061; BD_UPN=12314753; BA_HECTOR=21a00hag81al05a1d31h45em60r',
}#'User-Agent','Cookie'的值是在浏览器中检查源码的Network中的Headers中的Request Headers中的值，将二者通过字典存储。
res=requests.get(url,headers=headers)#将headers，url的值键入
resp=res.content.decode('utf-8')#转码->二进制码
print(resp)

三、Xpath

<supermarket>
    <name>永辉超市</name>
    <address>肖家河大厦</address>
    <goodsList>
        <goods name="泡面" price="3.5" count="20"></goods>
        <goods name="矿泉水" price="2" count="50"></goods>
        <goods name="面包" price="5" count="15"></goods>
    </goodsList>
    <worker_list>
        <cashier name="张三" pay="4000"></cashier>
        <shoppingGuide name="李四" pay="3500"></shoppingGuide>
    </worker_list>
    <goods price="50" count="15">
         <name>烟</name>
    </goods>

</supermarket>
#这是一段xml文件

#是一个树形结构
#根据路径选取相应的节点
#绝对路径写法：不管Xpath前面是什么，路径从根节点写---/绝对路径写法
#相对路径写法：用.代表节点，xpath前面是谁，当前节点就是谁，用..代表上层节点---./可以省略
#//路径-从任意位置搜索（全局搜索），与xpath的前面的节点无关

四、查找数据内容

#查找内容语法/text()
name=supermarket.xpath('./name/text()')
print(name)
names=supermarket.xpath('//name/text()')
print(names)
#获取节点属性值 语法-获取节点的路径/@属性名546655
r=supermarket.xpath('./goods/@price')
print(r)
rs=supermarket.xpath('//goods/@price')
print(rs)

五、确定需求信息（贝壳案例）

#贝壳
import csv
import random
import time
from lxml import etree
import requests
from time import sleep
# def delecteSqure(list):
#         for i in range(len(list)+1):
#                 for j in range(len(list[i])):
#                         if list[i]!=[]:
#                                 list[i][j]=list[i][j].spl
pages=range(1,3)
count=0
citys=['cd','nanchong','mianyang']
user_agents = [
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
        "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
        "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
        "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
        "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
        "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
        "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
        "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
        "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 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
        "Mozilla/4.0 (compatible; MSIE 7.0; 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)",
        "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/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
        "Mozilla/4.0 (compatible; MSIE 7.0; 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)",
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
        "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 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
        "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
        "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"
    ]#浏览器库，用来随机生成浏览器的user_agents
house=[]#在外面定义在里面定义会导致数据被覆盖
for city in citys:#从城市列表中选取数据来获取相应的城市的租房信息
        for page in pages:#获取第多少页数的数据
                time.sleep(2)
                url = f'https://{city}.zu.ke.com/zufang/pg{page}/#contentList'
                user_agent = random.choice(user_agents)
                headers={
                        'User-Agent': user_agent,
                        'Cookie': 'lianjia_uuid=c0ed8bea-1745-407f-9ee7-274cafc97638; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2217fd4d34ddd3ef-046fe4408a2a09-9771a3f-1327104-17fd4d34dde7e5%22%2C%22%24device_id%22%3A%2217fd4d34ddd3ef-046fe4408a2a09-9771a3f-1327104-17fd4d34dde7e5%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E8%87%AA%E7%84%B6%E6%90%9C%E7%B4%A2%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22https%3A%2F%2Fcn.bing.com%2F%22%2C%22%24latest_referrer_host%22%3A%22cn.bing.com%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC%22%7D%7D; select_city=510100; GUARANTEE_POPUP_SHOW=true; GUARANTEE_BANNER_SHOW=true; lianjia_ssid=dd1ae3bf-897c-43a2-84f0-71388cc28ff7; srcid=eyJ0Ijoie1wiZGF0YVwiOlwiMWE1N2IzYmFiNjNjZWVhMDg2MmY1NGVhZDhjYzU1ODE1ZGIzOGYwYzRkMGQ3NGYwNTBhODM1MDZmOWVlNzk4MGMyMzBlOGU1ZGNjMmIwYmFiYjA1YzJkMDM2YTgzNWNkZTNjMGYxN2M1MDJkYWViMzBlNTQzOTQwOWNiNGNmY2RjZjVkMWYyZjE0ZGViNjczNzdkNjVkYWU0OTM0NTIzOGM1ODZiZTYxODMwMGFlZjJhMTJmNzAzY2IwMzViMzdkNGI4MTlmZDc2MjBhYTI5MTRlZWYzZjAxZTZkM2JhZWEwNjE0MzFhYjY4YzJlYmY2NTFlY2QxYmExMjViNjk4MFwiLFwia2V5X2lkXCI6XCIxXCIsXCJzaWduXCI6XCIzYjM0MjhiOVwifSIsInIiOiJodHRwczovL2NkLnp1LmtlLmNvbS96dWZhbmciLCJvcyI6IndlYiIsInYiOiIwLjEifQ=='
                }#头部信息（隐藏爬虫身份）
                rsp=requests.get(url,headers=headers)
                parser=etree.HTMLParser(encoding='utf-8')#转码
                tree=etree.XML(rsp.text,parser=parser)
                house_list=tree.xpath('//*[@id="content"]/div[1]/div[1]/div')
        #//*[@id="content"]/div[1]/div[1]/div/div/p/a
        #//*[@id="content"]/div[1]/div[1]/div[1]/div/span/em
        #//*[@id="content"]/div[1]/div/div/div/p[2]/a
                for i in house_list:
                        name=i.xpath('./div/p[1]/a/text()')
                        price=i.xpath('./div/span/em/text()')
                        information=i.xpath('./div/p[2]/a/text()')
                        house.append([name,price,information])
                        count+=1
                # for i in range(len(house)+1):
                #         for j in range(3):
                #                 house[i][j]==house[i][j].replace('\n','')
                #                 house[i][j] == house[i][j].replace(' ', '')
                # for i in house:
                #         print(i)
                for i in house:#去除空格和
                        if i[1]!=[]:
                                i[0][0]=i[0][0].strip()
                                i[1][0] = i[1][0].strip()
                                i[2][0]=i[2][0].strip()
write=csv.writer(open('data1.csv','w',encoding='utf-8'))
write.writerow(['name','price','information'])
write.writerows(house)

六、图片爬取（二次元网图爬取）

import requests
url='https://api.ixiaowai.cn/api/api.php'#网址
pages=int(input())#想要下载的图片数
for i in range(pages):
    res = requests.get(url)
    data = res.content
    f=open(f'pig{i}.jpg','wb')
    f.write(data)
    f.close()