# coding=utf-8
from selenium import webdriver
import time

class DouYu:
    def __init__(self):
        self.start_url = "https://www.douyu.com/directory/all"
        self.driver = webdriver.Chrome()

    def get_content_list(self): #提取数据
        li_list = self.driver.find_elements_by_xpath("//ul[@id=‘live-list-contentbox‘]/li")
        content_list = []
        for li in li_list:
            item = {}
            item["title"] = li.find_element_by_xpath("./a").get_attribute("title")
            item["anchor"] = li.find_element_by_xpath(".//span[@class=‘dy-name ellipsis fl‘]").text
            item["watch_num"] = li.find_element_by_xpath(".//span[@class=‘dy-num fr‘]").text
            print(item)
            content_list.append(item)

        #提取下一页的元素
        next_url = self.driver.find_elements_by_xpath("//a[@class=‘shark-pager-next‘]")
        next_url = next_url[0] if len(next_url)>0 else None
        return content_list,next_url

    def save_content_list(self,content_lsit):#保存
        pass

    def run(self): #实现主要逻辑
        #1. start_url
        #2. 发送请求，获取响应
        self.driver.get(self.start_url)
        #3. 提取数据
        content_list,next_url = self.get_content_list()
        #4.保存
        self.save_content_list(content_list)

        # 5. 下一页数据的提取
        while next_url is not None:
            next_url.click() #页面没有完全加载完，会报错
            time.sleep(3)
            content_list,next_url = self.get_content_list()
            self.save_content_list(content_list)

if __name__ == ‘__main__‘:
    douyu = DouYu()
    douyu.run()

# coding=utf-8
from selenium import webdriver
import time

driver = webdriver.Chrome()
driver.get("https://mail.qq.com/")

driver.switch_to.frame("login_frame")
driver.find_element_by_id("u").send_keys("hello")

time.sleep(5)
driver.quit()

# coding=utf-8
import requests
from lxml import etree
import re
from selenium import webdriver
from copy import deepcopy

class Music163:
    def __init__(self):
        self.start_url = "http://music.163.com/discover/playlist"
        self.headers = {"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36"}
    def parse_url(self,url):
        print(url)
        resp = requests.get(url,headers=self.headers)
        return resp.content.decode()

    def get_category_list(self):#获取大分类和小分类
        resp = self.parse_url(self.start_url)
        html = etree.HTML(resp)
        dl_list = html.xpath("//div[@class=‘bd‘]/dl")
        category_list = []
        for dl in dl_list:
            b_cate = dl.xpath("./dt/text()")[0] if len(dl.xpath("./dt/text()"))>0 else None
            a_list = dl.xpath("./dd/a")
            for a in a_list:
                item = {}
                item["b_cate"]= b_cate
                item["s_cate"] = a.xpath("./text()")[0] if len(a.xpath("./text()"))>0 else None
                item["s_href"] = "http://music.163.com"+a.xpath("./@href")[0] if len(a.xpath("./@href"))>0 else None
                category_list.append(item)
        return category_list

    def get_playlist_list(self,item,total_playlist_list):#获取小分类中的playlist列表
        playlist_list = []
        if item["s_href"] is not None:
            scate_resp = self.parse_url(item["s_href"])
            scate_html = etree.HTML(scate_resp)
            li_list = scate_html.xpath("//ul[@id=‘m-pl-container‘]/li")
            for li in li_list:
                item["playlist_title"] = li.xpath("./p[@class=‘dec‘]/a/@title")[0] if len(li.xpath("./p[@class=‘dec‘]/a/@title"))>0 else None
                print(item["playlist_title"])
                item["playlist_href"] = "http://music.163.com"+li.xpath("./p[@class=‘dec‘]/a/@href")[0] if len(li.xpath("./p[@class=‘dec‘]/a/@href"))>0 else None
                item["author_name"] = li.xpath("./p[last()]/a/@title")[0] if len(li.xpath("./p[last()]/a/@title"))>0 else None
                item["author_href"] = "http://music.163.com"+li.xpath("./p[last()]/a/@href")[0] if len(li.xpath("./p[last()]/a/@href"))>0 else None
                playlist_list.append(deepcopy(item))
            total_playlist_list.extend(playlist_list)
            next_url = scate_html.xpath("//a[text()=‘下一页‘]/@href")[0] if len(scate_html.xpath("//a[text()=‘下一页‘]/@href"))>0 else None
            if next_url is not None and next_url!=‘javascript:void(0)‘:
                item["s_href"] = "http://music.163.com"+next_url
                #递归，调用自己，获取下一页的播放列表，直到下一页没有的时候不再递归
                return self.get_playlist_list(item,total_playlist_list)
        return total_playlist_list

    def get_playlist_info(self,playlist): #获取单个播放别表的信息
        if playlist["playlist_href"] is not None:
            playlist_resp = self.parse_url(playlist["playlist_href"])
            playlist["covers"] = re.findall("\"images\": .*?\[\"(.*?)\"\],",playlist_resp)
            playlist["covers"] =  playlist["covers"][0] if len(playlist["covers"])>0 else None
            playlist["create_time"] = re.findall("\"pubDate\": \"(.*?)\"",playlist_resp)
            playlist["create_time"] = playlist["create_time"][0] if len(playlist["create_time"])>0 else None
            playlist_html = etree.HTML(playlist_resp)
            playlist["favorited_times"] = playlist_html.xpath("//a[@data-res-action=‘fav‘]/@data-count")[0] if len(playlist_html.xpath("//a[@data-res-action=‘fav‘]/@data-count"))>0 else None
            playlist["shared_times"] = playlist_html.xpath("//a[@data-res-action=‘share‘]/@data-count")[0] if len(playlist_html.xpath("//a[@data-res-action=‘share‘]/@data-count"))>0 else None
            playlist["desc"] = playlist_html.xpath("//p[@id=‘album-desc-dot‘]/text()")
            playlist["played_times"] = playlist_html.xpath("//strong[@id=‘play-count‘]/text()")[0] if len(playlist_html.xpath("//strong[@id=‘play-count‘]/text()"))>0 else None
            playlist["tracks"] = self.get_playlist_tracks(playlist["playlist_href"])
            return playlist

    def get_playlist_tracks(self,href): #获取每个歌单的歌曲信息
        driver = webdriver.Chrome()
        driver.get(href)
        driver.switch_to.frame("g_iframe")
        tr_list = driver.find_elements_by_xpath("//tbody/tr")
        playlist_tracks = []
        for tr in tr_list:
            track = {}
            track["name"] = tr.find_element_by_xpath("./td[2]//b").get_attribute("title")
            track["duration"] = tr.find_element_by_xpath("./td[3]/span").text
            track["singer"] = tr.find_element_by_xpath("./td[4]/div").get_attribute("title")
            track["album_name"] = tr.find_element_by_xpath("./td[5]//a").get_attribute("title")
            playlist_tracks.append(track)
        driver.quit()
        return playlist_tracks



    def run(self):
        categroy_list = self.get_category_list() #获取分类
        for cate in categroy_list:
            total_playlist_list = self.get_playlist_list(cate,[]) #获取每个分类下的所有播放列表
            print("-"*100)
            print(total_playlist_list)
            print("-"*100)
            for playlist in total_playlist_list:
                print(playlist,"*"*100)
                playlist = self.get_playlist_info(playlist)  #获取每个播放列表下的所有歌曲信息
                print(playlist)

if __name__ == ‘__main__‘:
    music_163 = Music163()
    music_163.run()
 

    

import time

# 基本用法
# from selenium import webdriver
# driver = webdriver.Chrome()
# driver.get("http:\\www.baidu.com")
# driver.save_screenshot(‘./baidu.png‘)
# time.sleep(2)
# driver.quit()

# 无界面使用方法
# from selenium import webdriver
# from selenium.webdriver.chrome.options import Options
#
# chrome_options = Options()
# chrome_options.add_argument(‘--headless‘)
# driver = webdriver.Chrome(chrome_options=chrome_options)
# driver.get("http:\\www.baidu.com")
# driver.save_screenshot(‘./baidu.png‘)
# time.sleep(1)
# driver.quit()

# 跳转窗口用法
from selenium import webdriver
from selenium.webdriver.chrome.options import Options

# chrome_options = Options()
# chrome_options.add_argument(‘--headless‘)
# driver = webdriver.Chrome(chrome_options=chrome_options)

# driver = webdriver.Chrome()
# 获取当前窗口句柄 句柄一般指唯一标识符
# now_handle = driver.current_window_handle
# 获取所有窗口句柄
# all_handles = driver.window_handles
# 切换回原窗口
# driver.switch_to_window(now_handle)
# time.sleep(2)

# 设置代理
# from selenium import webdriver
# chromeOptions = webdriver.ChromeOptions()

# 一定要注意，=两边不能有空格，不能是这样--proxy-server = http://202.20.16.82:10152
# chromeOptions.add_argument("--proxy-server=http://202.20.16.82:10152")
# browser = webdriver.Chrome(chrome_options = chromeOptions)

# 设置请求头
# from selenium import webdriver
# options = webdriver.ChromeOptions()
# 设置中文
# options.add_argument(‘lang=zh_CN.UTF-8‘)
# 更换头部
# options.add_argument(‘user-agent="Mozilla/5.0 (iPod; U; CPU iPhone OS 2_1 like Mac OS X; ja-jp) AppleWebKit/525.18.1 (KHTML, like Gecko) Version/3.1.1 Mobile/5F137 Safari/525.20"‘)
# browser = webdriver.Chrome(chrome_options=options)
# url = "https://httpbin.org/get?show_env=1"
# browser.get(url)
# browser.quit()

# 设置不加载图片
from selenium import webdriver

# options = webdriver.ChromeOptions()
# prefs = {
#     ‘profile.default_content_setting_values‘: {
#         ‘images‘: 2
#     }
# }
# options.add_experimental_option(‘prefs‘, prefs)
# browser = webdriver.Chrome(chrome_options=options)

# browser = webdriver.Chrome()
# url = "http://image.baidu.com/"
# browser.get(url)
# input("是否有图")
# browser.quit()

from selenium import webdriver
options = webdriver.ChromeOptions()
prefs = {
    ‘profile.default_content_setting_values‘: {
        ‘images‘: 2  # 2表示禁用图片加载,提高速度
    }
}
options.add_experimental_option(‘prefs‘, prefs)
options.add_argument(‘--headless‘)
driver = webdriver.Chrome(chrome_options=options)

driver.get("https://www.kaishiba.com/project/more")
driver.save_screenshot(‘./startBa.png‘)
while True:
    js = "window.scrollTo(0,document.body.scrollHeight)" # 模拟浏览器的下拉动作
    driver.execute_script(js)
    # time.sleep(random.randint(2,5))
    l_list = driver.find_elements_by_xpath("//li[@class=‘programCard‘]")
    print(‘获取%d条数据‘ % len(l_list))
    if len(l_list)==1800:
        with open(‘./start.html‘,‘w‘,encoding=‘utf-8‘) as f:
            f.write(driver.page_source)
        break

driver.quit()

import requests
import json
import time

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 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 

username = ‘whoarewe‘ # 用户名

password = ‘***‘ # 密码

appid = 4283 # appid

appkey = ‘02074c64f0d0bb9efb2df455537b01c3‘ # appkey

filename = ‘getimage.jpg‘ # 文件位置

codetype = 1004 # 验证码类型

# 超时
timeout = 60

def indetify(response_content):
    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(response_content, codetype, timeout)
        print(‘cid: %s, result: %s‘ % (cid, result))
        return result

def indetify_by_filepath(file_path):
    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(file_path, codetype, timeout)
        print(‘cid: %s, result: %s‘ % (cid, result))
        return result

if __name__ == ‘__main__‘:
    pass