爬成语小程序返回的结果是错误的，求大佬帮忙看看
import requestsfrom bs4 import BeautifulSoup
import re
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36'
}
def getChengyu(cate, page):
f=open("chengyu_urls.csv","a",encoding="utf-8")
res=requests.get("https://www.chengyucidian.net/letter/"+str(cate)+"/p/"+str(page), headers=headers, allow_redirects=False)
res.encoding="utf-8"
soup=BeautifulSoup(res.text)
urls=soup.select('div')
print(urls)
urls=re.findall('\d+',str(urls))
for url in urls:
f.write("https://www.chengyucidian.net/cy/"+str(url)+".html"+"\n")
def getPageNum(cate):
res = requests.get("https://www.chengyucidian.net/letter/"+str(cate), headers=headers, allow_redirects=False)
res.encoding="utf-8"
soup=BeautifulSoup(res.text)
pagenum=soup.select('div')
pagenum=re.findall('\d+',str(pagenum))[-1]
return pagenum
def getIntroduction(url):
res = requests.get(url, headers=headers, allow_redirects=False)
res.encoding = "utf-8"
soup = BeautifulSoup(res.text)
chengyu=soup.select('h1')
chengyu=str(chengyu).replace("<h1>","")
chengyu=chengyu.replace("</h1>","")
print(chengyu)
introText = soup.select('div')
introText=str(introText).replace("<p>","")
introText = introText.replace("</p>", "")
introText = introText.replace('<h4 id="chu">', "")
introText = introText.replace('<h4 id="shi">', "")
introText = introText.replace('</h4>', "")
introText = introText.replace('<h4>', "")
introText = introText.replace('<div class="con">', "")
introText = introText.replace('</div>', "")
introText = introText.replace('<strong>', "")
introText = introText.replace('</strong>', "")
introText = introText.replace('<p class="ciLs">', "")
print(introText)
return chengyu, introText
if __name__=="__main__":
f1=open("chengyu_urls.csv","r",encoding="utf-8")
f2=open("chengyu_introText.csv","a",encoding="utf-8")
urls=f1.read().split("\n")
print(len(urls))
for url in urls:
chengyu,introText=getIntroduction(url)
f2.write(str(chengyu)+"\n"+"["+str(introText)+"]"+"\n")
返回值：
>>>
===================== RESTART: C:\Users\wepie\Desktop\11.py ====================
2
>>>
{:5_109:}去年跟着甲鱼学Python，今年差不多已经还给小甲鱼了。最近想重新开始学习，有一个爬虫小程序是他人写的，我想使用一下，但是返回值是2，也没有其它报错，请大佬指导下{:10_266:}{:10_266:}{:10_266:} chengyu_urls.csv读取分割之后就2个元素，所以打印2。
页:
[1]