倚天屠龙记小说列表:URL
https://www.2biqukan.com/fiction/zsczu/contents.html
实现代码
from urllib import request
from bs4 import BeautifulSoup
if __name__ == "__main__":
index_url = "https://www.2biqukan.com/fiction/zsczu.html"
header={
'User-Agent': 'Mozilla/5.0 (Linux; Android 4.1.1; Nexus 7 Build/JRO03D) AppleWebKit/'
'535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Safari/535.19'
}
#指定url,header生成request
url_req = request.Request(index_url,headers=header)
#打开url,并获得请求内容response
response = request.urlopen(url_req)
#读取response的内容,用gbk解码,得到html内容
html = response.read().decode('utf-8', 'ignore')
#用BeautifulSoup处理得到的网页html
html_soup = BeautifulSoup(html,'lxml')
index = BeautifulSoup(str(html_soup.find_all('ul', class_='list-group novel-index ro