import requests
import re
url = 'https://live.500.com/'
browser_headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
html = requests.get(url, headers=browser_headers)
# 中文乱码 源文件编码为gb2312
html.encoding = 'gb2312'
# 网页内容存到 content中
content = html.text
# print(html.text)
# 正则表达式 预加载
re_1 = re.compile(r'<td align="center" class=""><input type=.*?/>(?P<num>.*?)'
r'</td>.*?<td align="right" class="p_lr01">.*?/">(?P<team1>.*?)'
r'</a>.*?<td align="left" class="p_lr01">.*?">(?P<team2>.*?)</a>', re.S)
# 迭代器
s = re_1.finditer(content)
for i in s:
print(i.group('num'),"{}:{}".format(i.group("team1"),i.group("team2")))
html.close()
# print(resp.text)
# print(html.encoding)
500彩票 足彩赛事(正则表达式)
最新推荐文章于 2024-04-23 14:01:52 发布