记录python的selenium使用
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from bs4 import BeautifulSoup
import sys
import urllib.parse
if len(sys.argv) <= 1:
exit()
#对输入的词进行urlencode
queryword = urllib.parse.quote_plus(str(sys.argv[1]))
#设置chrome的执行方式为headless;即非打开窗口执行
chrome_options = Options()
chrome_options.add_argument("--headless")
driver = webdriver.Chrome(chrome_options=chrome_options)
url = "https://hanyu.baidu.com/zici/s?wd="+queryword+"&query="+queryword+"&srcid=28232&from=kg0&from=kg0";
driver.get("https://hanyu.baidu.com/zici/s?wd="+queryword+"&query="+queryword+"&srcid=28232&from=kg0&from=kg0")
htmldata = driver.page_source
print(htmldata)
driver.quit()
print("您输入查询的词是:"+sys.argv[1])
soup = BeautifulSoup(htmldata,'html.parser');
#得到查询文字拼音
pinyin_dt =soup.find('dt',class_='pinyin');
if not pinyin_dt:
pingyin_div=soup.find('div',id='pinyin');
if not pingyin_div:
print("拼音:未查询到:(")
else:
pingyin_b = pingyin_div.find('b')
if not pingyin_b:
print("拼音:"+pingyin_div.string.strip())
else:
print("拼音:"+pingyin_b.string.strip())
else:
print("拼音:"+pinyin_dt.string.strip())
#得到查询文字的基本释义
basicmean_div = soup.find("div",id="basicmean-wrapper")
if basicmean_div:
basicmean_ps = basicmean_div.find_all("p")
count = 1;
if basicmean_ps:
for basicmean_p in basicmean_ps:
basicmean_p = str(basicmean_p)
if basicmean_p:
basicmean_p = basicmean_p.replace("","")
basicmean_p = basicmean_p.replace("
","")
basicmean_p = basicmean_p.replace("","")
basicmean_p = basicmean_p.replace("","")
print("基本释义("+str(count)+"):"+basicmean_p.strip())
count +=1
#得到查询文字的翻译
fanyi_div = soup.find("div",id="fanyi-wrapper")
if fanyi_div:
fanyi_dt = fanyi_div.find("dt")
if fanyi_dt:
print("英文翻译:"+fanyi_dt.string.strip())
网页标题:记录python的selenium使用
当前网址:http://ybzwz.com/article/goccse.html