发布时间:2019-09-01 09:51:05编辑:auto阅读(2082)
该小脚本实现对电影天堂网站的最新电影查找。
from bs4 import BeautifulSoup import urllib import re url= 'http://www.ygdy8.net/html/gndy/dyzz/index.html' moive_url_list = [] moive_name_list = [] request = urllib.urlopen(url) response = request.read() response = unicode(response,'GBK').encode('utf-8') soup = BeautifulSoup(response,'html.parser') a = soup.find_all('a',class_="ulink") for i in a: moive_open_url = 'http://www.ygdy8.net' + i['href'] req = urllib.urlopen(moive_open_url) res = req.read() try: res = unicode(res,'GBK').encode('utf-8') except UnicodeDecodeError: continue so = BeautifulSoup(res,'html.parser') a_tag = so.find_all('a') for j in a_tag: pattern = re.compile("^ftp://ygdy\d{1}:ygdy\d{1}@y\d{3}.dydytt.net") string= j['href'] match = pattern.match(string) if match: moive_url_list.append(string) for m in moive_url_list: print m
上一篇: python的while循环
下一篇: Python3.6 和 Pycharm
47870
46434
37323
34767
29338
26002
24953
19971
19571
18059
5812°
6437°
5953°
5980°
7086°
5930°
5972°
6463°
6428°
7805°