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 urllib.request
from bs4 import BeautifulSoup
import re
url = 'https://www.biduo.cc/biquge/39_39888/c13353637.html'
headers = {
'Accept-Language': 'zh-CN',
'Cache-Control': 'no-cache',
'Connection': 'Keep-Alive',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18363'
}
res = urllib.request.Request(url=url,headers=headers)
response = urllib.request.urlopen(res)
html = response.read().decode("gbk",'ignore')
regular = re.compile(".*?<br><br> ")
m = regular.findall(html)
for each in m:
each = each[:-32]
print(' ',end='')
if ' ' in each :
print(each.split(';')[-1])
else:
print(each)
搞了个爬虫爬了一张小说,有没有大佬给改得更精简好用让我观摩一下
import urllib.request
import re
url = 'https://www.biduo.cc/biquge/39_39888/c13353637.html'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 '
'(KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18363'
}
response = urllib.request.urlopen(urllib.request.Request(url=url, headers=headers))
html = response.read().decode("gbk", 'ignore')
for each in re.findall(".*?<br><br> ", html):
each = each[:-32]
print(' ', (each.split(';')[-1] if ' ' in each else each))
|