from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from bs4 import BeautifulSoup
import time,re
 
path = Service("D:\\MyDrivers\\chromedriver.exe")#
# 配置不顯示瀏覽器
chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
chrome_options.add_argument('User-Agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36')
 
# 創(chuàng)建Chrome實(shí)例 。
 
driver = webdriver.Chrome(service=path,options=chrome_options)
lst=["happy","help","evening","great","think","adapt"]
 
for word in lst:
    url="https://skell.sketchengine.eu/#result?lang=en&query="+word+"&f=concordance"
    driver.get(url)
    # 刷新網(wǎng)頁(yè)獲取新數(shù)據(jù)
    driver.refresh()
    time.sleep(2)
    # page_source——》獲得頁(yè)面源碼
    resp=driver.page_source
    # 解析源碼
    soup=BeautifulSoup(resp,"html.parser")
    table = soup.find_all("td")
    with open("eps.txt",'a+',encoding='utf-8') as f:
        f.write(f"\n{word}的例子\n")
    for i in table[0:6]:
        text=i.text
        #替換多余的空格
        new=re.sub("\s+"," ",text)
        #寫(xiě)入txt文本
        with open("eps.txt",'a+',encoding='utf-8') as f:
            f.write(re.sub(r"^(\d+\.)",r"\n\1",new))
driver.close()

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from bs4 import BeautifulSoup
import time,re
import os
 
# 配置模擬瀏覽器的位置
path = Service("D:\\MyDrivers\\chromedriver.exe")#
# 配置不顯示瀏覽器
chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
chrome_options.add_argument('User-Agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36')
 
# 創(chuàng)建Chrome實(shí)例 。
 
def get_wordlist():
    wordlist=[]
    with open("wordlist.txt",'r',encoding='utf-8') as f:
        lines=f.readlines()
        for line in lines:
            word=line.strip()
            wordlist.append(word)
    return wordlist
 
def main(lst):
    driver = webdriver.Chrome(service=path,options=chrome_options)
    for word in lst:
        url="https://skell.sketchengine.eu/#result?lang=en&query="+word+"&f=concordance"
        driver.get(url) 
        driver.refresh()
        time.sleep(2)
        # page_source——》頁(yè)面源碼
        resp=driver.page_source
        # 解析源碼
        soup=BeautifulSoup(resp,"html.parser")
        table = soup.find_all("td")
        with open("examples.txt",'a+',encoding='utf-8') as f:
            f.writelines(f"\n{word}的例子\n")
        for i in table[0:6]:
            text=i.text
            new=re.sub("\s+"," ",text)
            with open("eps.txt",'a+',encoding='utf-8') as f:
                f.write(new)
#                 f.writelines(re.sub("(\.\s)(\d+\.)","\1\n\2",new))
 
if __name__=="__main__":
    lst=get_wordlist()
    main(lst)
    os.startfile("examples.txt")