python+selenium的一个小蜘蛛

用selenium玩的是精准打击.
这是爬取指定汉字的笔顺拼音声音的小爬虫。速度慢，但是指向很灵活。只需要调整 yourtxt.txt 里面的
文件内容即可。

#coding:utf-8
from urllib.request import urlretrieve

from selenium import webdriver
from selenium.webdriver.support import expected_conditions as ec
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from time import sleep
import re

address = 'https://hanyu.baidu.com/'
shz = ' '
url = ' '

op = webdriver.FirefoxOptions()
op.add_argument("--headless")   #等效于 ———— op.set_headless()
op.add_argument("--disable-gpu")    #禁用GPU加速
driver = webdriver.Firefox(firefox_options = op)
driver.get(address)
ele = WebDriverWait(driver,10,0.2).until(ec.title_contains('百度汉语'))

def getvalue(shz):
    try:
        #ele = WebDriverWait(driver,10,0.2).until(ec.title_contains('百度汉语'))
        trg = driver.find_element_by_id('kw')
        trg.clear()
        trg.send_keys(shz)
        trg = driver.find_element_by_id('su')
        trg.click()
        print(shz)
    except:
        print('程序出现错误，请调试解决后运行')
        exit()
        quit()
    
    try:
        trg = driver.find_element_by_id('pc--body')
        trg = driver.find_element_by_xpath(r'//*[@id="data-container"]/div[1]/div[1]/a')
        trg.click()
        print('有夹层')
    except:
        print('无夹层')
    finally:
        ele = WebDriverWait(driver,10).until(ec.visibility_of(driver.find_element(by=By.ID,value='pc-word-body')))

        trg = driver.find_element_by_xpath(r'//*[@id="word_bishun"]')       #抓取字符动画
        url = trg.get_attribute('src')
        urlretrieve(url,'./image/'+ shz + '.gif')                           #保存为以字符为名字的gif动图
        print(url)

        trg = driver.find_element_by_xpath(r'//*[@id="pinyin"]/span/a')     #抓取读音
        url= trg.get_attribute('url')
        urlretrieve(url,'./mp3/'+ shz + '.mp3')                             #保存为以字符为名字的mp3格式
        print(url)
        
        pinyin = driver.find_element_by_xpath(r'//*[@id="pinyin"]/span/b').text
        print(pinyin)

        driver.back()
        with open('pinyi.txt','a+',encoding = ('UTF-8-sig')) as f:
            f.writelines(shz + ',' + pinyin + '\n')
        ele = WebDriverWait(driver,10,0.2).until(ec.title_contains('百度汉语'))
        print('抓取成功')

#   main()：
txt = []
with open('yourtxt.txt','r',encoding = ('UTF-8-sig')) as f:
    txt = f.readlines()

for i in range(len(txt)):
    try:
        print(i + 1)
        d = txt[i][-2]
        getvalue(d)
    except Exception as e:
        print(e)

driver.close()
driver.quit()