|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
import requests
import bs4
import re
def open_url(url):
headers={
'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400'
}
res = requests.get(url,headers=headers)
return res
def find_animation(res):
soup = bs4.BeautifulSoup(res.text,'html.parser')
#动漫名
animation = []
targets = soup.find_all("li",class_="anime_icon2")
for each in targets:
animation.append(each.h4.a.text)
#集数
jishu = []
targets = soup.find_all("span",class_="anime_icon1_name1")
for each in targets:
jishu.append(each.text)
#找出一共多少个页面
def find_depth(res):
soup = bs4.BeautifulSoup(res.text,'html.parser')
depth = soup.find('li',class_='pbutton asciifont').previous_sibling.previous_sibling.text
return int(depth)
def main():
host = "https://www.agefans.tv/recommend"
res = open_url(host)
depth = find_depth(res)
result = []
#length = len(animation)
for i in range(depth):
url = host + '/?start=' + str(25 * i)
res = open_url(url)
result.extend(find_animation(res))
with open("age动漫推荐.txt","w",encoding="utf-8")as f:
for each in result:
f.write(each)
这句:
depth = soup.find('li',class_='pbutton asciifont').previous_sibling.previous_sibling.text
我看了那个网站,li没有这个class,是下面的a有class。
另外这个语句应该是不对的,应该改一下,你是想拿什么数据?
|
|