python爬虫下载某网站156个网页小游戏素材
本帖最后由 三木猿 于 2020-9-18 23:19 编辑有哪些游戏自己看吧↓
一波网页小游戏（摸鱼专用）
https://www.52pojie.cn/thread-1269936-1-1.html
压缩包内有广告，管理员不让发，难受，马上升级了还给我积分撤回了
下载网页小游戏素材版：
import requests
from bs4 import BeautifulSoup
def get_Url(url):
str_list = []
content = requests.get(url).content
soup = BeautifulSoup(content, 'lxml')
find = soup.find('span', attrs={'class': 'current'})
sum = int(find.text.split('/'))
for i in range(sum):
if i == 0:
str_list.append('https://www.mycodes.net/166/')
continue
str_list.append('https://www.mycodes.net/166/' + str(i + 1) + '.htm')
return str_list
def get_document(url):
soup = BeautifulSoup(requests.get(url).content, 'lxml')
find_all = soup.find_all('a', attrs={'style': 'color:#006BCD;font-size:14px;'})
a = ''
for value in find_all:
if a.__eq__(str(value['href'])):
continue
a = value['href']
document = BeautifulSoup(requests.get(value['href']).content, 'lxml')
text = document.find('td', attrs={'class': 'a0'}).text
print(text+":")
td_s = document.find_all('td', attrs={'class': 'b4'})
for td in td_s:
find = td.find('a')
if find is not None:
href_ = 'https://www.mycodes.net' + find['href']
down = requests.get(href_)
with open('d:/SanMu/'+text+".zip", "wb") as code:
code.write(down.content)
break
if __name__ == '__main__':
url_list = get_Url('https://www.mycodes.net/166/')
for url in url_list:
get_document(url)
获取在线网址版：
成品如上
以下是代码
import requestsfrom bs4 import BeautifulSoup
def get_Url(url):
str_list = []
content = requests.get(url).content
soup = BeautifulSoup(content, 'lxml')
find = soup.find('span', attrs={'class': 'current'})
sum = int(find.text.split('/'))
for i in range(sum):
if i == 0:
str_list.append('https://www.mycodes.net/166/')
continue
str_list.append('https://www.mycodes.net/166/' + str(i + 1) + '.htm')
return str_list
def get_document(url):
soup = BeautifulSoup(requests.get(url).content, 'lxml')
find_all = soup.find_all('a', attrs={'style': 'color:#006BCD;font-size:14px;'})
a = ''
for value in find_all:
if a.__eq__(str(value['href'])):
continue
a = value['href']
document = BeautifulSoup(requests.get(value['href']).content, 'lxml')
text = document.find('td', attrs={'class': 'a0'}).text
print(text+":")
td_s = document.find_all('td', attrs={'class': 'b1'})
for td in td_s:
find = td.find('a')
if find is not None:
print(find['href'])
if __name__ == '__main__':
url_list = get_Url('https://www.mycodes.net/166/')
for url in url_list:
get_document(url)
火钳刘明 冒昧打搅，想麻烦带佬爬一下4399小游戏的素材和源码
http://www.4399.com/flash/10916.htm#search3
跪谢！跪谢！跪谢！ down = requests.get(url=href_,verify=False)
代码ssl报错的小伙伴
42行这样改 感谢分享，最近开始自学这个
页:
[1]