python爬虫爬取猫眼电影Top100,每一页有10个电影,但是爬虫只能爬取第一个,后面都爬不到不止是为什么
代码如下,大神帮忙看看,感激不尽
import requests
from requests.exceptions import RequestException
import re
def get_one_page(url):
try:
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36'}
response=requests.get(url,headers=headers)
if response.status_code==200:
return response.text
return None
except RequestException:
return None
def parse_one_page(html):
pattern=re.compile('
'.*?star">(.*?).*?releasetime">(.*?).*?integer">(.*?).*?fraction">(.*?).*?
items=re.findall(pattern,html)
print(items)
def main():
url='http://maoyan.com/board/4?'
html=get_one_page(url)
parse_one_page(html)
if name=='__main__':
main()
结果显示
C:\Users\Administrator\python37\python.exe C:/Users/Administrator/PycharmProjects/Maoyantop100/spder.py
[('1', 'https://p1.meituan.net/movie/20803f59291c47e1e116c11963ce019e68711.jpg@160w_220h_1e_1c', '霸王别姬', '\n 主演:张国荣,张丰毅,巩俐\n ', '上映时间:1993-01-01', '9.', '5')]
Process finished with exit code 0