爬虫之旅（五）

最新推荐文章于 2022-11-21 18:20:40 发布

Simplicity_

最新推荐文章于 2022-11-21 18:20:40 发布

阅读量290

点赞数

分类专栏： spider 学习笔记

本文链接：https://blog.csdn.net/hensonwells/article/details/78322725

版权

学习笔记同时被 2 个专栏收录

89 篇文章 1 订阅

订阅专栏

spider

18 篇文章 0 订阅

订阅专栏

__author__ = 'Administrator'
from  bs4 import BeautifulSoup
from selenium.common.exceptions import NoSuchElementException
from img_get import get_img

import selenium
import sys
import time
import re
import csv
import pytesser


if __name__ == "__main__":
    import os
    from selenium import webdriver
    from selenium.webdriver.support.ui import WebDriverWait

    f = open("/home/henson/Documents/coding/bill/criminal.csv", "a+", encoding='utf-8')

    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}

    chromedriver = "/home/henson/Documents/pycharm/webdriver/chromedriver"
    os.environ["webdriver.chrome.driver"] = chromedriver
    driver = webdriver.Chrome(chromedriver)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
    driver.get('http://......')
    # inputElement = driver.find_element_by_xpath("//*[@id='b_Text0']")#//*[@id="b_Text0"]

    # driver.switch_to_frame('iframeResult')  # 定位到页面元素
    driver.find_element_by_xpath('/html/body/div[3]/ul/li[1]/a/div[1]').click()

    try:
        for i in range(1, 10000):
            title = driver.find_element_by_xpath('/html/body/div[3]/div[1]/div[1]/div[2]').text
            court = driver.find_element_by_xpath('/html/body/div[3]/div[1]/div[1]/div[3]').text
            text = driver.find_element_by_xpath('/html/body/div[3]/div[1]/div[1]/div[5]').text
            #title = title.replace(",", "")
            print(title)
            print(court)
            print(text)

            data = (title, court, text)

            writer = csv.writer(f)
            writer.writerows(data)

            driver.find_element_by_xpath('//*[@id="linkNextOne"]').click()

    except NoSuchElementException:
        verificationCode=driver.current_url #获取验证码的链接
        get_img(verificationCode)           #获取验证码

import pytesser
# 打开验证码界面

import os
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
chromedriver = "/home/henson/Documents/pycharm/webdriver/chromedriver"
os.environ["webdriver.chrome.driver"] = chromedriver
driver = webdriver.Chrome(chromedriver)
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")

def get_img(url):

    driver.get(url)
    # 获取截图整个页面
    driver.get_screenshot_as_file('screenshot.png')

    # 获取指定元素位置
    element = driver.find_element_by_id('imgCode')
    left = int(element.location['x'])
    top = int(element.location['y'])
    right = int(element.location['x'] + element.size['width'])
    bottom = int(element.location['y'] + element.size['height'])

    # 通过Image处理图像
    im = Image.open('screenshot.png')
    im = im.crop((left, top, right, bottom)) #进行裁剪得到验证码
    im.save('code.png')

# encoding=utf-8
from PIL import Image
from PIL import ImageEnhance
#from pytesser import *
import sys
sys.path.append('/home/henson/Documents/coding/bill/pytesser/')
from  pytesser.pytesser import *


img = Image.open('screenshot.png')

#img=Image.open('code.png')

#使用ImageEnhance可以增强图片的识别率
enhancer = ImageEnhance.Contrast(img)
image_enhancer = enhancer.enhance(4)  #识别验证码
print (image_to_string(image_enhancer)) #返回验证码结果