上传

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/firstpyproject.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.12 (firstpyproject)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12 (firstpyproject)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/firstpyproject.iml" filepath="$PROJECT_DIR$/.idea/firstpyproject.iml" />
+    </modules>
+  </component>
+</project>

get_contend.py

@@ -0,0 +1,61 @@
+import  requests
+import  json
+from lxml import etree
+import js2py
+import  login
+USERNAME="td188310339"
+PASSWORD="Aa123456"
+COOKIE=login(USERNAME,PASSWORD)
+HEADERS={
+    'Cookies':COOKIE
+}
+BASE_URL='https://www.tadu.com/'
+def get_id(num):
+    text =requests.get(f'{BASE_URL}/book/988681/{num+1}/?isfirstpart=true',headers=HEADERS).text
+    html=etree.HTML(text)
+    return html.xpath('//a[@id="paging_left"]/@href')[0].strip().split('/')[-1]
+for chapter_num in range (1,101):
+    js_code = """
+    function encipher(e) {
+        var a = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
+          , t = "="
+          , o = function(e) {
+            var o, s = "", i = e.length;
+            for (o = 0; i - 2 > o; o += 3)
+                s += a[e.charCodeAt(o) >> 2],
+                s += a[((3 & e.charCodeAt(o)) << 4) + (e.charCodeAt(o + 1) >> 4)],
+                s += a[((15 & e.charCodeAt(o + 1)) << 2) + (e.charCodeAt(o + 2) >> 6)],
+                s += a[63 & e.charCodeAt(o + 2)];
+            return i % 3 && (o = i - i % 3,
+            s += a[e.charCodeAt(o) >> 2],
+            i % 3 == 2 ? (s += a[((3 & e.charCodeAt(o)) << 4) + (e.charCodeAt(o + 1) >> 4)],
+            s += a[(15 & e.charCodeAt(o + 1)) << 2],
+            s += t) : (s += a[(3 & e.charCodeAt(o)) << 4],
+            s += t + t)),
+            s
+        };
+        return o(e)
+    }
+    """
+    encipher = js2py.eval_js(js_code)
+
+    chapter_id = get_id(1)
+
+    dataLimit = encipher(chapter_id)
+
+    print(dataLimit)
+
+    res = requests.get(f'{BASE_URL}getPartContentByCodeTable/988681/{chapter_num},headers=HEADERS)')
+
+    text = res.text
+
+    text = json.loads(text)
+
+    text = text['data']['content']
+
+    html = etree.HTML(text)
+
+    texts = html.xpath(f'//p[not(constains(@data-limit,"{dataLimit}"))]/text()')
+
+    for txt in texts:
+        print(txt)

login.py

@@ -0,0 +1,196 @@
+import random
+
+from selenium import webdriver
+from selenium.webdriver import ActionChains
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+import time
+import cv2
+import pytesseract
+import requests
+import os
+import numpy as np
+from io import BytesIO
+from PIL import Image
+from selenium.webdriver import ChromeOptions
+driver = webdriver.Chrome()
+
+# 打开登录页面
+driver.get('https://www.tadu.com/v3/loginpage?logintype=taduphone')
+# 等待账号输入框可见
+
+# 去除浏览器识别
+option = ChromeOptions()
+#隐藏浏览器
+option.add_argument('--headlless')
+option.add_argument('--disable-gpu')
+
+
+def get_tracks(distance):
+    distance += 20
+    v = 0
+    t = 0.2
+    forward_tracks = []
+    current = 0
+    mid = distance * 3 / 5
+    while current < distance:
+        if current < mid:
+            a = 2
+        else:
+            a = -3
+        s = v * t + 0.5 * a * (t ** 2)
+        v = v + a * t
+        current += s
+        forward_tracks.append(round(s))
+
+    back_tracks = [-3, -3, -2, -2, -2, -2, -2, -1, -1, -1]
+    return {'forward_tracks': forward_tracks, 'back_tracks': back_tracks}
+
+
+def crack_slider(tracks):
+    wait = WebDriverWait(driver, 5)
+
+    slider = wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'tc-drag-thumb')))
+    ActionChains(driver).click_and_hold(slider).perform()  # 模拟按住鼠标左键
+
+    for track in tracks['forward_tracks']:
+        ActionChains(driver).move_by_offset(xoffset=track, yoffset=0).perform()
+
+    time.sleep(0.5)
+    for back_tracks in tracks['back_tracks']:
+        ActionChains(driver).move_by_offset(xoffset=back_tracks, yoffset=0).perform()
+    print("1212313")
+    ActionChains(driver).move_by_offset(xoffset=-4, yoffset=0).perform()
+    ActionChains(driver).move_by_offset(xoffset=4, yoffset=0).perform()
+    time.sleep(0.5)
+
+    ActionChains(driver).release().perform()  # 释放左键
+    return 0
+
+
+# 下载图片到本地
+def get_image(img_url,imgname):
+    # 以流的形式下载文件
+    image=requests.get(img_url,stream=True)
+    imgName = ''.join(["./", imgname])
+    with open(imgName, 'wb') as f:
+        for chunk in image.iter_content(chunk_size=1024): # 循环写入  chunk_size：每次下载的数据大小
+            if chunk:
+                f.write(chunk)
+                f.flush()
+        f.close()
+
+def get_image_offset(background_image_url, slider_image_url):
+    back_image = 'back_image.png'  # 背景图像命名
+
+    slider_image = 'slider_image.png'  # 滑块图像命名
+
+    get_image(background_image_url, back_image)
+
+    get_image(slider_image_url, slider_image)
+
+    # 获取图片并灰度化
+    block = cv2.imread(slider_image, 0)
+
+    template = cv2.imread(back_image, 0)
+
+    w, h = block.shape[::-1]
+    # print(w, h)
+    # 二值化后图片名称
+    block_name = 'block.jpg'
+    template_name = 'template.jpg'
+    # 保存二值化后的图片
+    cv2.imwrite(block_name, block)
+
+    cv2.imwrite(template_name, template)
+
+    block = cv2.imread(block_name)
+
+    block = cv2.cvtColor(block, cv2.COLOR_RGB2GRAY)
+
+    block = abs(255 - block)
+
+    cv2.imwrite(block_name, block)
+
+    block = cv2.imread(block_name)
+
+    template = cv2.imread(template_name)
+
+    # 获取偏移量
+    # 模板匹配，查找block在template中的位置，返回result是一个矩阵，是每个点的匹配结果
+    result = cv2.matchTemplate(block, template, cv2.TM_CCOEFF_NORMED)
+
+    x, y = np.unravel_index(result.argmax(), result.shape)
+
+    print(x, y)
+    # 由于获取到的验证码图片像素与实际的像素有差(实际：280*158 原图：680*390)，故对获取到的坐标进行处理
+    offset = y * (295 / 680)
+
+    # 画矩形圈出匹配的区域
+    # 参数解释：1.原图 2.矩阵的左上点坐标 3.矩阵的右下点坐标 4.画线对应的rgb颜色 5.线的宽度
+    cv2.rectangle(template, (y, x), (y + w, x + h), (7, 249, 151), 2)
+
+    show(template)
+
+    return offset
+# 显示图片
+def show(name):
+
+	cv2.imshow('Show', name)
+
+	cv2.waitKey(0)
+
+	cv2.destroyAllWindows()
+
+# 实现规避检测
+option.add_experimental_option('excludeSwitches', ['enable-automation'])
+option.add_experimental_option("detach", True)
+# 采取去除特征识别，即以下两行代码。
+script = 'Object.defineProperty(navigator, "webdriver", {get: () => false,});'
+driver.execute_script(script)
+
+js = 'return window.navigator.webdriver'
+print(driver.execute_script(js))  # 可以直接在终端输出webdriver检测结果
+
+
+option.add_experimental_option('excludeSwitches', ['enable-automation'])
+option.add_experimental_option("detach", True)
+
+account_switch=WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, 'phoneAccountSwitch')))
+account_switch.click()
+
+username_input = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CLASS_NAME, 'accountInput')))
+password_input = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CLASS_NAME, 'accountPass')))
+
+username_input.send_keys('td188310339')  # 用户名
+password_input.send_keys('Aa123456')  # 密码
+
+submit = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CLASS_NAME, 'accountLogin_bt')))
+submit.click()
+
+frame=WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, 'tcaptcha_iframe')))
+driver.switch_to.frame(frame)
+time.sleep(10)
+
+img=WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, 'slideBg')))
+image_url = img.get_attribute('src')  # 图片的URL
+
+img2=WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, 'slideBlock')))
+image2_url = img2.get_attribute('src')  # 图片的URL
+
+x=get_image_offset(image_url,image2_url)
+print(x)
+
+drag_button =WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, 'tcaptcha_drag_thumb')))
+
+ActionChains(driver).click_and_hold(drag_button).perform()
+time.sleep(0.5)
+# 遍历轨迹进行滑动
+time.sleep(0.01)
+crack_slider(get_tracks(x))
+
+time.sleep(2)
+cookies = driver.get_cookies()
+cookies=''.join([f'{cookie["name"]}={cookie["value"]};' for cookie in cookies])
+print(cookies)