爬虫重要案例总结与回顾

最新推荐文章于 2023-10-25 14:30:00 发布

weixin_30670925

最新推荐文章于 2023-10-25 14:30:00 发布

阅读量293

点赞数

文章标签：爬虫 json 操作系统

原文链接：http://www.cnblogs.com/haitaoli/p/10633237.html

版权

一.爬取化妆品生产许可证相关
二.爬取肯德基餐厅查询指定地点
三.正则 - 爬取糗事百科图片
四.bs4 - 爬取诗词名句网站中三国演义小说
五.xpath解析相关实例
六.图片懒加载
七.使用云打码平台识别验证码
八.模拟登录人人网,爬取个人中心页面数据
九.对古诗文网进行模拟登录
十.使用线程池爬取梨视频的视频数据
十一.selenium的使用

一.爬取化妆品生产许可证相关

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
}


def get_ID(pages):
    url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList'

    ID_list = []

    for every_page in range(1, pages + 1):

        params = {
            "on": "true",
            "page": str(every_page),
            "pageSize": "15",
            "productName": "",
            "conditionType": "1",
            "applyname": "",
            "applysn": "",
        }

        data = requests.post(url=url, params=params, headers=headers).json()

        for each_dict in data["list"]:
            ID_list.append(each_dict['ID'])

        import time
        time.sleep(0.1)

    return ID_list


def get_all_detail(ID_list):
    url = "http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById"

    with open('化妆品生产许可证信息.txt', 'a', encoding='utf-8') as f:
        for ID in ID_list:
            params = {
                "id": ID
            }

            data = requests.post(url=url, params=params, headers=headers).text

            f.write(data + '\n')

            import time
            time.sleep(0.1)

    print("数据写入文件成功!")


ID_list = get_ID(10)
get_all_detail(ID_list)

二.爬取肯德基餐厅查询指定地点

import requests

# UA伪装
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
}

# 指定url
url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'

# 处理参数
area = input('请输入一个地名: ')
params = {
    "cname": "",
    "pid": "",
    "keyword": area,
    "pageIndex": "1",
    "pageSize": "10",
}

# 发起请求,获取响应数据
data = requests.get(url=url, params=params, headers=headers).json()

print(data)

三.正则 - 爬取糗事百科图片

import re
import os
import time
import requests
from urllib import request

if not os.path.exists('./qiutu'):
    os.mkdir('/qiutu')

url = "https://www.qiushibaike.com/pic/"

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}

page_text = requests.get(url=url, headers=headers).text

if not os.path.exists('qiutu'):
    os.mkdir('qiutu')

img_url_list = re.findall('<div class="thumb">.*?<img src="(.*?)" alt.*?</div>', page_text, re.S)

for img_url in img_url_list:
    img_url = 'https:' + img_url
    img_name = img_url.split('/')[-1]
    img_path = './qiutu/' + img_name
    request.urlretrieve(img_url, img_path)
    print(img_path, '下载成功!')

    time.sleep(0.1)

四.bs4 - 爬取诗词名句网站中三国演义小说

import requests
from bs4 import BeautifulSoup

headers={
         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
     }
def parse_content(url):
    #获取标题正文页数据
    page_text = requests.get(url,headers=headers).text
    soup = BeautifulSoup(page_text,'lxml')
    #解析获得标签
    ele = soup.find('div',class_='chapter_content')
    content = ele.text #获取标签中的数据值
    return content

if __name__ == "__main__":
     url = 'http://www.shicimingju.com/book/sanguoyanyi.html'
     reponse = requests.get(url=url,headers=headers)
     page_text = reponse.text

     #创建soup对象
     soup = BeautifulSoup(page_text,'lxml')
     #解析数据
     a_eles = soup.select('.book-mulu > ul > li > a')
     print(a_eles)
     cap = 1
     for ele in a_eles:
         print('开始下载第%d章节'%cap)
         cap+=1
         title = ele.string
         content_url = 'http://www.shicimingju.com'+ele['href']
         content = parse_content(content_url)

         with open('./sanguo.txt','w') as fp:
             fp.write(title+":"+content+'\n\n\n\n\n')
             print('结束下载第%d章节'%cap)

五.xpath解析相关实例

1.解析58二手房的相关数据

import requests
from lxml import etree

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}

url = 'https://bj.58.com/ershoufang/?PGTID=0d200001-0000-1376-eb9f-25ca6cacedce&ClickID=1'

page_text = requests.get(url=url, headers=headers).text

# 数据解析
tree = etree.HTML(page_text)

li_list = tree.xpath('//ul[@class="house-list-wrap"]/li')

if __name__ == '__main__':

    for li in li_list:
        title = li.xpath('./div[2]/h2/a/text()')[0].strip()
        print(title)

2.下载彼岸图网中的图片数据:中文乱码问题

import requests, os
from lxml import etree
from urllib import request

# 创建一个空文件夹,用于存放图片数据
if not os.path.exists('./images'):
    os.mkdir('./images')

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}

url = 'http://pic.netbian.com/4kmeinv/'

# 获取响应数据
page_text = requests.get(url=url, headers=headers).text

# 实例化etree对象
tree = etree.HTML(page_text)
# xpath解析
li_list = tree.xpath('//div[@class="slist"]/ul/li')

for li in li_list:
    img_name = li.xpath('./a/img/@alt')[0]
    # 处理中文乱码问题
    img_name = img_name.encode('ISO-8859-1').decode('gbk')

    img_url = 'http://pic.netbian.com' + li.xpath('./a/img/@src')[0]
    img_path = './images/' + img_name + '.jpg'
    request.urlretrieve(url=img_url, filename=img_path)
    print("下载完成!!!")

3.下载煎蛋网中图片数据(数据经过加密)

from lxml import etree
from urllib import request
import requests
import base64
import os

if not os.path.exists('./jiandan'):
    os.mkdir('./jiandan')

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}

url = 'http://jandan.net/ooxx/page-62'

page_text = requests.get(url=url, headers=headers).text

tree = etree.HTML(page_text)

img_hash_list = tree.xpath('//span[@class="img-hash"]/text()')

for img_hash in img_hash_list:
    # 图片的真实url(需要用base64解码)
    img_url = "http:" + base64.b64decode(img_hash).decode('utf8')

    # 设置图片存放路径
    img_path = './jiandan/' + img_url.split('/')[-1]

    # 持久化存储
    request.urlretrieve(url=img_url, filename=img_path)
    print("下载完成!!", img_url)

print('over!')

4.下载站长素材中的简历模板数据

import requests
import random
import os
from lxml import etree

if not os.path.exists('./jianli'):
    os.mkdir('./jianli')

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}

for i in range(1, 6):
    # 1.指定url
    if i == 1:
        url = 'http://sc.chinaz.com/jianli/free.html'
    else:
        url = f'http://sc.chinaz.com/jianli/free_{i}.html'
    # 2.发起请求
    response = requests.get(url=url, headers=headers)
    # 2.1编码格式
    response.encoding = 'utf8'
    # 3.获取响应的文本信息
    page_text = response.text
    # 4.实例化etree对象,将页面源码加载到该对象中
    tree = etree.HTML(page_text)
    # 5.使用xpath函数进行定位
    a_list = tree.xpath('//a[@class="title_wl"]')

    for a in a_list:
        jianli_name = a.xpath('./text()')[0]
        jianli_url = a.xpath('./@href')[0]
        print(jianli_name)
        print(jianli_url)
        print('----------------------------------------------')

        response2 = requests.get(url=jianli_url, headers=headers)
        response2.encoding = 'utf8'
        each_jinali_text = response2.text
        tree2 = etree.HTML(each_jinali_text)
        # 所有下载地址列表
        download_url_list = tree2.xpath('//div[@class="clearfix mt20 downlist"]/ul/li/a/@href')
        # 随机选择一个下载地址
        download_url = random.choice(download_url_list)
        # 获取响应的数据
        res = requests.get(url=download_url, headers=headers).content
        # 持久化存储
        filepath = './jianli/' + jianli_name + '.rar'
        with open(filepath, 'wb') as f:
            f.write(res)
        print(jianli_name, '下载完成!')

print('over!')

5.解析所有城市名称

"""
解析所有城市名称
https://www.aqistudy.cn/historydata/
"""

import requests
from lxml import etree

url = 'https://www.aqistudy.cn/historydata/'

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}

response = requests.get(url=url, headers=headers)
response.encoding = 'utf8'
page_text = response.text
tree = etree.HTML(page_text)

hot_city_list = tree.xpath('//div[@class="hot"]/div[2]/ul/li/a/text()')
all_city_list = tree.xpath('//div[@class="all"]/div[2]/ul/div[2]/li/a/text()')
# 可以用管道符连接以上二者
cityname_list = tree.xpath(
    '//div[@class="hot"]/div[2]/ul/li/a/text() | //div[@class="all"]/div[2]/ul/div[2]/li/a/text()')

print('-----------------------------------------------------------')
print(hot_city_list)

print('***********************************************************')
print(all_city_list)

print('###########################################################')
print(cityname_list)

六.图片懒加载

"""
图片懒加载概念:
    - 图片懒加载是一种网页优化技术.图片作为一种网络资源,
    在被请求时也与普通静态资源一样,将占用网络资源,
    而一次性将整个页面的所有图片加载完,
    将大大增加页面的首屏加载时间.为了解决这种问题,通过前后端配合,
    使图片仅在浏览器当前视窗内出现时才加载该图片,
    达到减少首屏图片请求数的技术就被称为"图片懒加载".

网站一般如何实现图片懒加载技术呢?
    - 在网页源码中,在img标签中首先会使用一个"伪属性"(通常使用src2,original...)
    去存放真正的图片链接而并非是直接存放在src属性中.当图片出现到页面的可视化区域中,
    会动态将伪属性替换成src属性,完成图片的加载.
"""

import os
import requests
from urllib import request
from lxml import etree

if not os.path.exists('./images'):
    os.mkdir('./images')

url = 'http://sc.chinaz.com/tupian/'

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}

response = requests.get(url=url, headers=headers)
response.encoding = 'utf8'
page_text = response.text
tree = etree.HTML(page_text)
img_list = tree.xpath('//div[@class="box picblock col3"]/div/a/img')

for img in img_list:
    img_name = img.xpath('./@alt')[0]
    img_url = img.xpath('./@src2')[0]

    file_path = './images/' + img_name + '.jpg'
    request.urlretrieve(img_url, file_path)
    print("下载完成!!!", img_name)

print('over!')

"""
站长素材案例后续分析:
    - 通过细致观察页面的结构后发现,网页中图片的链接是存储在了src2这个伪属性中
"""

七.使用云打码平台识别验证码

ydmhttp.py:

import http.client, mimetypes, urllib, json, time, requests


class YDMHttp:
    apiurl = 'http://api.yundama.com/api.php'
    username = ''
    password = ''
    appid = ''
    appkey = ''

    def __init__(self, username, password, appid, appkey):
        self.username = username
        self.password = password
        self.appid = str(appid)
        self.appkey = appkey

    def request(self, fields, files=[]):
        response = self.post_url(self.apiurl, fields, files)
        response = json.loads(response)
        return response

    def balance(self):
        data = {'method': 'balance', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['balance']
        else:
            return -9001

    def login(self):
        data = {'method': 'login', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['uid']
        else:
            return -9001

    def upload(self, filename, codetype, timeout):
        data = {'method': 'upload', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'codetype': str(codetype), 'timeout': str(timeout)}
        file = {'file': filename}
        response = self.request(data, file)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['cid']
        else:
            return -9001

    def result(self, cid):
        data = {'method': 'result', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'cid': str(cid)}
        response = self.request(data)
        return response and response['text'] or ''

    def decode(self, filename, codetype, timeout):
        cid = self.upload(filename, codetype, timeout)
        if (cid > 0):
            for i in range(0, timeout):
                result = self.result(cid)
                if (result != ''):
                    return cid, result
                else:
                    time.sleep(1)
            return -3003, ''
        else:
            return cid, ''

    def report(self, cid):
        data = {'method': 'report', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'cid': str(cid), 'flag': '0'}
        response = self.request(data)
        if (response):
            return response['ret']
        else:
            return -9001

    def post_url(self, url, fields, files=[]):
        for key in files:
            files[key] = open(files[key], 'rb');
        res = requests.post(url, files=files, data=fields)
        return res.text

# 该函数用于获取识别后的验证码
def getCodeData(username, password, filename, codetype, timeout):
    # 用户名
    username = username

    # 密码
    password = password

    # 软件ＩＤ，开发者分成必要参数。登录开发者后台【我的软件】获得！
    appid = 1234

    # 软件密钥，开发者分成必要参数。登录开发者后台【我的软件】获得！
    appkey = 'xxx'

    # 图片文件
    filename = filename

    # 验证码类型，# 例：1004表示4位字母数字，不同类型收费不同。请准确填写，否则影响识别率。在此查询所有类型 http://www.yundama.com/price.html
    codetype = codetype

    # 超时时间，秒
    timeout = timeout

    # 检查
    if (username == 'username'):
        print('请设置好相关参数再测试')
    else:
        # 初始化
        yundama = YDMHttp(username, password, appid, appkey)

        # 登陆云打码
        uid = yundama.login();
        print('uid: %s' % uid)

        # 查询余额
        balance = yundama.balance();
        print('balance: %s' % balance)

        # 开始识别，图片路径，验证码类型ID，超时时间（秒），识别结果
        cid, result = yundama.decode(filename, codetype, timeout);
        print('cid: %s, result: %s' % (cid, result))
    return result

八.模拟登录人人网,爬取个人中心页面数据

"""
cookie的处理:
1. 手动处理
    - cookie封装到headers
2. 自动处理
    - (1)获取一个session对象
    - (2)使用session对象进行请求的发送
    - (3)作用: 在使用session进行请求发送的过程中如果产生了cookie,
            则cookie会被自动存储到session对象中.
"""


from ydmhttp import getCodeData # 识别人人网中的验证码图片
import requests
from urllib import request
from lxml import etree

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}
url = 'http://www.renren.com'

page_text = requests.get(url=url, headers=headers).text
tree = etree.HTML(page_text)
code_img_url = tree.xpath('//*[@id="verifyPic_login"]/@src')[0]

if code_img_url:
    request.urlretrieve(url=code_img_url, filename='./code.jpg')
    # 识别验证码图片中的数据值,2004表示4位纯汉字，其他类型代码参考云打码帮助文档
    # 查看验证码类型: http://www.yundama.com/price.html
    code_data = getCodeData('username', 'password', './code.jpg', 2004, 30)
    print(code_data)  # code_data为识别结果
else:
    print('不需要识别验证码')
    code_data = ''

# 指定登录请求的url
login_url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2019241516668'
data = {    # 以下数据通过fiddler抓包工具抓取到网页后即可拿到
    "email": "xxx",     # 你的email
    "icode": code_data,
    "origURL": "http://www.renren.com/home",
    "domain": "renren.com",
    "key_id": "1",
    "captcha_type": "web_login",
    "password": "xxx",  # 你的password密文
    "rkey": "xxx",
    "f": "http%3A%2F%2Fwww.renren.com%2F970153909"
}

# 创建session对象
session = requests.Session()
# 使用session进行请求的发送: 获取cookie,且将cookie保存到session中
session.post(url=login_url, data=data, headers=headers)
# 指定个人主页对应的页面url
url = 'http://www.renren.com/970153909/profile'
# 携带session发送该请求,并获取响应数据
page_text = session.get(url=url, headers=headers).text
# 持久化存储
with open('renren.html', 'w', encoding='utf8') as f:
    f.write(page_text)

九.对古诗文网进行模拟登录

"""
cookie的处理:
    1. 手动处理:
        - 把cookie封装到headers中
    2. 自动处理:
        - (1)获取一个session对象
        - (2)使用session对象进行请求的发送
        - (3)作用: 在使用session进行请求发送的过程中,
                如果产生了cookie,cookie就会被自动存储到session对象中.
"""


from ydmhttp import getCodeData # 识别人人网中的验证码图片
from urllib import request
from lxml import etree
import requests, os, uuid

# 创建资源文件存放目录
if not os.path.exists('./sources'):
    os.mkdir('./sources')

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}

# 实例化session对象
session = requests.Session()

# 指定登陆页面的url
url = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
# 获取登陆页面的HTML文本
page_text = requests.get(url=url, headers=headers).text
# 创建etree对象
tree = etree.HTML(page_text)

# 获取登陆页面的识别验证码
code_img_url = 'https://so.gushiwen.org' + tree.xpath('//*[@id="imgCode"]/@src')[0]
# 持久化存储 验证码图片
filepath = f'./sources/{uuid.uuid4()}'
filename = filepath + '.jpg'
# 注意:验证码图片必须用携带session去获取,否则获取的验证码无法该账户相匹配
img_data = session.get(url=code_img_url, headers=headers).content
with open(filename, 'wb') as fp:
    fp.write(img_data)

# 识别验证码图片中的数据. 验证码类型查询: http://www.yundama.com/price.html
# 这里应该填写你云打码平台 普通用户的用户名和密码,而不是开发者用户; 1004是验证码类型, 50是延迟时间
code_data = getCodeData('username', 'password', filename, 1004, 50)

# 指定登录请求的url
login_url = 'https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx'

# 登录该网站时需要在请求头中加入动态参数
__VIEWSTATE = tree.xpath('//*[@id="__VIEWSTATE"]/@value')[0]
__VIEWSTATEGENERATOR = tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')[0]
data = {
    "__VIEWSTATE": __VIEWSTATE,
    "__VIEWSTATEGENERATOR": __VIEWSTATEGENERATOR,
    "from": "http://so.gushiwen.org/user/collect.aspx",
    "email": "xxx",     # 你的email
    "pwd": "xxx",       # 你的密码
    "code": code_data,
    "denglu": "登录",
}

# 模拟登陆,拿到登录后的首页数据
index_text = session.post(url=login_url, data=data, headers=headers).content

# 持久化存储
filename2 = filepath + '.html'
with open(filename2, 'wb') as f:
    f.write(index_text)

print('下载成功!!!')

十.使用线程池爬取梨视频的视频数据

import requests, re, os
from lxml import etree
from uuid import uuid4

# 导入线程池模块
from multiprocessing.dummy import Pool

# 在线程池中创建10个线程
pool = Pool(10)
"""
线程池的使用场景: 应用在所有耗时的操作中
"""

# 创建资源文件存放目录
if not os.path.exists('./sources'):
    os.mkdir('./sources')

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}

url = 'https://www.pearvideo.com/category_1'
page_text = requests.get(url=url, headers=headers).text
tree = etree.HTML(page_text)
li_list = tree.xpath('//*[@id="listvideoListUl"]/li')
video_url_list = []  # 装的是所有视频链接地址
for li in li_list:
    detail_url = 'https://www.pearvideo.com/' + li.xpath('./div/a/@href')[0]
    print(detail_url)
    detail_page_text = requests.get(url=detail_url, headers=headers).text
    # 我们发现,视频的链接地址在JS中,无法通过xpath取到视频链接地址,于是采用正则匹配
    video_url = re.findall('ldUrl="",srcUrl="(.*?)",vdoUrl=srcUrl', detail_page_text, re.S)[0]
    video_url_list.append(video_url)
print(video_url_list)


def getVideoData(url):
    video_data = requests.get(url=url, headers=headers).content
    return video_data


def saveVideoData(data):
    filename = f'./sources/{uuid4()}.mp4'
    with open(filename, 'wb') as f:
        f.write(data)
    print('下载成功!')


# 对视频的链接发起请求并获取视频数据
# video_data_list存储所有视频的二进制数据
video_data_list = pool.map(getVideoData, video_url_list)

# 使用线程池对视频数据进行持久化存储
pool.map(saveVideoData, video_data_list)

十一.selenium的使用

博客地址: https://www.cnblogs.com/bobo-zhang/p/9685362.html

谷歌浏览器驱动下载地址: http://chromedriver.storage.googleapis.com/index.html

下载的驱动程序必须和浏览器的版本统一，大家可以根据http://blog.csdn.net/huilan_same/article/details/51896672中提供的版本映射表进行对应

PhantomJS下载地址: https://pan.baidu.com/s/11KMIKitILGpVU33oxxzcJA  # 提取码：og8o

1.百度文本输入框中录入中国

"""
selenium: 可以让浏览器完成相关自动化的操作
环境安装:
    - pip install selenium
编码流程:
    - 导包
    - 创建某一款浏览器对象
    - 制定相关的行为动作
"""

from selenium import webdriver
import time, os

if not os.path.exists('./sources'):
    os.mkdir('./sources')

# 配置浏览器
browser = webdriver.Chrome(executable_path=r'F:\chromedriver.exe')
time.sleep(3)

browser.get('https://www.baidu.com/')
time.sleep(3)

# find系列的函数可以帮助我们定位到相关的标签
text_input = browser.find_element_by_id('kw')
# 向文本框录入一个关键字
text_input.send_keys('中国')
time.sleep(3)

btn = browser.find_element_by_id('su')
btn.click()
time.sleep(3)

# 获取当前浏览器显示的页面源码数据(动态加载的数据)
page_text = browser.page_source

# 持久化存储
with open('./sources/zhongguo.html', 'w', encoding='utf-8') as fp:
    fp.write(page_text)

time.sleep(3)

browser.quit()

2.爬取更多的电影详情数据(豆瓣)

from selenium import webdriver
import time, os

if not os.path.exists('./sources'):
    os.mkdir('./sources')

# 配置浏览器
browser = webdriver.Chrome(executable_path=r'F:\chromedriver.exe')

browser.get('https://movie.douban.com/typerank?type_name=%E7%88%B1%E6%83%85&type=13&interval_id=100:90&action=')
time.sleep(3)

browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
time.sleep(3)
browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
time.sleep(3)
browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
time.sleep(3)

# 获取浏览器当前的页面源码数据
page_text = browser.page_source

# 持久化存储
with open('./sources/douban.html', 'w', encoding='utf-8') as fp:
    fp.write(page_text)

time.sleep(3)

browser.quit()

3.使用phantomJs浏览器爬取更多的电影详情数据(豆瓣)

from selenium import webdriver
import time, os

if not os.path.exists('./sources'):
    os.mkdir('./sources')

# 配置PhantomJS浏览器
browser = webdriver.PhantomJS(
    executable_path=r'F:\phantomjs-2.1.1-windows\bin\phantomjs.exe')

browser.get('https://movie.douban.com/typerank?type_name=%E7%88%B1%E6%83%85&type=13&interval_id=100:90&action=')
time.sleep(3)

browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
time.sleep(3)
browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
time.sleep(3)
browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
time.sleep(3)

# 获取浏览器当前的页面源码数据
page_text = browser.page_source

# 持久化存储
with open('./sources/douban2.html', 'w', encoding='utf-8') as fp:
    fp.write(page_text)

time.sleep(3)

browser.quit()

4.使用谷歌无头浏览器爬取数据

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from time import sleep

# 必须写上这三个配置项
chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
# 指定chrome_options
bro = webdriver.Chrome(executable_path=r'C:\Users\chromedriver.exe', chrome_options=chrome_options)
sleep(3)

bro.get('https://www.baidu.com/')
sleep(3)

# find系列的函数可以帮助我们定位到相关的标签
text_input = bro.find_element_by_id('kw')
# 向文本框中录入一个关键字
text_input.send_keys('中国')
sleep(3)

btn = bro.find_element_by_id('su')
btn.click()
sleep(3)

# 获取当前浏览器显示的页面源码数据（动态加载的数据）
page_text = bro.page_source
print(page_text)

bro.quit()

5.登录qq空间并爬取首页的数据

from selenium import webdriver
from lxml import etree
import time, os

if not os.path.exists('./sources'):
    os.mkdir('./sources')

# 配置浏览器
browser = webdriver.Chrome(executable_path=r'F:\chromedriver.exe')

# 发送请求
browser.get('https://qzone.qq.com/')
time.sleep(5)

"""
在web应用中经常会遇到frame嵌套页面的应用,
使用WebDriver每次只能在一个页面上识别元素,
对于frame嵌套内的页面上的元素,
直接定位是定位不到的.
这个时候就需要通过switch_to.frame()方法
将当前定位的主体切换到frame里
"""

# 定位到id="login_frame"的iframe标签下的所有元素
browser.switch_to.frame('login_frame')

# 点击id="switcher_plogin"的标签
browser.find_element_by_id('switcher_plogin').click()
time.sleep(1)

# 给id="u"的标签设置值
browser.find_element_by_id("u").send_keys("username")   # 你的用户名
# time.sleep(1)

# 给id="p"的标签设置值
browser.find_element_by_id("p").send_keys("password")   # 你的密码
# time.sleep(3)

# 点击id="login_button"的标签设置值
browser.find_element_by_id("login_button").click()
time.sleep(1)

browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
time.sleep(1)
browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
time.sleep(1)

# 获取页面所有数据
page_text = browser.page_source

# 持久化存储
with open('./sources/QQzone.html', 'w', encoding='utf-8') as fp:
    fp.write(page_text)

tree = etree.HTML(page_text)

li_list = tree.xpath('//*[@id="feed_friend_list"]/li')

for li in li_list:
    text_list = li.xpath('.//div[@class="f-info"]//text() | .//div[@class="f-info qz_info_cut"]//text()')
    text = ''.join(text_list)
    print(text + '\n\n\n')

browser.close()

转载于:https://www.cnblogs.com/haitaoli/p/10633237.html