이 글은 주로 python3 Baidu 인덱스 크롤링을 소개합니다. 편집자는 이것이 꽤 좋다고 생각합니다. 이제 여러분과 공유하고 참고용으로 제공하겠습니다. 편집자를 따라가서 살펴보겠습니다.
바이두 지수를 파악한 후 이미지 인식을 사용해 지수를 얻습니다
서문:
투푸는 바이두 지수가 파악하기 어렵고 비용이 20이라고 말한 적이 있습니다. 타오바오 항목당 만원 키워드:
사람이 어떻게 그 사람을 두려워할 수 있어서 2일 반 정도 걸려서 완성했어요. 🎜>
설치된 라이브러리가 많습니다:谷歌图像识别tesseract-ocr pip3 install pillow pip3 install pyocr selenium2.45 Chrome47.0.2526.106 m or Firebox32.0.1 chromedriver.exe
# 打开浏览器 def openbrowser(): global browser # http://www.php.cn/ url = "https://passport.baidu.com/v2/?login&tpl=mn&u=http%3A%2F%2Fwww.baidu.com%2F" # 打开谷歌浏览器 # Firefox() # Chrome() browser = webdriver.Chrome() # 输入网址 browser.get(url) # 打开浏览器时间 # print("等待10秒打开浏览器...") # time.sleep(10) # 找到id="TANGRAM__PSP_3__userName"的对话框 # 清空输入框 browser.find_element_by_id("TANGRAM__PSP_3__userName").clear() browser.find_element_by_id("TANGRAM__PSP_3__password").clear() # 输入账号密码 # 输入账号密码 account = [] try: fileaccount = open("../baidu/account.txt") accounts = fileaccount.readlines() for acc in accounts: account.append(acc.strip()) fileaccount.close() except Exception as err: print(err) input("请正确在account.txt里面写入账号密码") exit() browser.find_element_by_id("TANGRAM__PSP_3__userName").send_keys(account[0]) browser.find_element_by_id("TANGRAM__PSP_3__password").send_keys(account[1]) # 点击登陆登陆 # id="TANGRAM__PSP_3__submit" browser.find_element_by_id("TANGRAM__PSP_3__submit").click() # 等待登陆10秒 # print('等待登陆10秒...') # time.sleep(10) print("等待网址加载完毕...") select = input("请观察浏览器网站是否已经登陆(y/n):") while 1: if select == "y" or select == "Y": print("登陆成功!") print("准备打开新的窗口...") # time.sleep(1) # browser.quit() break elif select == "n" or select == "N": selectno = input("账号密码错误请按0,验证码出现请按1...") # 账号密码错误则重新输入 if selectno == "0": # 找到id="TANGRAM__PSP_3__userName"的对话框 # 清空输入框 browser.find_element_by_id("TANGRAM__PSP_3__userName").clear() browser.find_element_by_id("TANGRAM__PSP_3__password").clear() # 输入账号密码 account = [] try: fileaccount = open("../baidu/account.txt") accounts = fileaccount.readlines() for acc in accounts: account.append(acc.strip()) fileaccount.close() except Exception as err: print(err) input("请正确在account.txt里面写入账号密码") exit() browser.find_element_by_id("TANGRAM__PSP_3__userName").send_keys(account[0]) browser.find_element_by_id("TANGRAM__PSP_3__password").send_keys(account[1]) # 点击登陆sign in # id="TANGRAM__PSP_3__submit" browser.find_element_by_id("TANGRAM__PSP_3__submit").click() elif selectno == "1": # 验证码的id为id="ap_captcha_guess"的对话框 input("请在浏览器中输入验证码并登陆...") select = input("请观察浏览器网站是否已经登陆(y/n):") else: print("请输入“y”或者“n”!") select = input("请观察浏览器网站是否已经登陆(y/n):")
# 新开一个窗口,通过执行js来新开一个窗口 js = 'window.open("http://index.baidu.com");' browser.execute_script(js) # 新窗口句柄切换,进入百度指数 # 获得当前打开所有窗口的句柄handles # handles为一个数组 handles = browser.window_handles # print(handles) # 切换到当前最新打开的窗口 browser.switch_to_window(handles[-1])
# 清空输入框 browser.find_element_by_id("schword").clear() # 写入需要搜索的百度指数 browser.find_element_by_id("schword").send_keys(keyword) # 点击搜索 # <input type="submit" value="" id="searchWords" onclick="searchDemoWords()"> browser.find_element_by_id("searchWords").click() time.sleep(2) # 最大化窗口 browser.maximize_window() # 构造天数 sel = int(input("查询7天请按0,30天请按1,90天请按2,半年请按3:")) day = 0 if sel == 0: day = 7 elif sel == 1: day = 30 elif sel == 2: day = 90 elif sel == 3: day = 180 sel = '//a[@rel="' + str(day) + '"]' browser.find_element_by_xpath(sel).click() # 太快了 time.sleep(2)
xoyelement = browser.find_elements_by_css_selector("#trend rect")[2]
from selenium.webdriver.common.action_chains import ActionChains ActionChains(browser).move_to_element_with_offset(xoyelement,x_0,y_0).perform()
x_0 = 1 y_0 = 0
# 按照选择的天数循环 for i in range(day): # 构造规则 if day == 7: x_0 = x_0 + 202.33 elif day == 30: x_0 = x_0 + 41.68 elif day == 90: x_0 = x_0 + 13.64 elif day == 180: x_0 = x_0 + 6.78
# <p class="imgtxt" style="margin-left:-117px;"></p> imgelement = browser.find_element_by_xpath('//p[@id="viewbox"]')
이 상자의 크기와 위치를 결정합니다.
# 找到图片坐标 locations = imgelement.location print(locations) # 找到图片大小 sizes = imgelement.size print(sizes) # 构造指数的位置 rangle = (int(locations['x']), int(locations['y']), int(locations['x'] + sizes['width']), int(locations['y'] + sizes['height']))
# 构造指数的位置 rangle = (int(locations['x'] + sizes['width']/3), int(locations['y'] + sizes['height']/2), int(locations['x'] + sizes['width']*2/3), int(locations['y'] + sizes['height']))
这个写法最终不太好,最起码要对keyword的长度进行判断,长度过长会导致截图坐标出现偏差,反正我知道怎么做,就是不写出来给你们看!
后面的完整代码是:
# <p class="imgtxt" style="margin-left:-117px;"></p> imgelement = browser.find_element_by_xpath('//p[@id="viewbox"]') # 找到图片坐标 locations = imgelement.location print(locations) # 找到图片大小 sizes = imgelement.size print(sizes) # 构造指数的位置 rangle = (int(locations['x'] + sizes['width']/3), int(locations['y'] + sizes['height']/2), int(locations['x'] + sizes['width']*2/3), int(locations['y'] + sizes['height'])) # 截取当前浏览器 path = "../baidu/" + str(num) browser.save_screenshot(str(path) + ".png") # 打开截图切割 img = Image.open(str(path) + ".png") jpg = img.crop(rangle) jpg.save(str(path) + ".jpg")
但是后面发现裁剪的图片太小,识别精度太低,所以需要对图片进行扩大:
# 将图片放大一倍 # 原图大小73.29 jpgzoom = Image.open(str(path) + ".jpg") (x, y) = jpgzoom.size x_s = 146 y_s = 58 out = jpgzoom.resize((x_s, y_s), Image.ANTIALIAS) out.save(path + 'zoom.jpg', 'png', quality=95)
原图大小请 右键->属性->详细信息 查看,我的是长73像素,宽29像素
最后就是图像识别
# 图像识别 index = [] image = Image.open(str(path) + "zoom.jpg") code = pytesseract.image_to_string(image) if code: index.append(code)
最后效果图:
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持PHP中文网。
更多python3 Baidu 인덱스 크롤링 예제에 대한 자세한 설명相关文章请关注PHP中文网!