首先感谢崔庆才大神的课程，本文代码基本都是取之于他所授视频
import json
from multiprocessing import Pool
import requests
from requests.exceptions import RequestException
import re
def get_one_page(url):
try:
response = requests.get(url)
if response.status_code == 200:
return response.text
return None
except RequestException:
return None
def parse_one_page(html):
pattern = re.compile('<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name"><a'
+'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
+'.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
items = re.findall(pattern,html)
for item in items:
yield{
'index':item[0],
'image':item[1],
'title':item[2],
'actor':item[3].strip()[3:],
'time':item[4].strip()[5:],
'score':item[5]+item[6]
}
def main():
for offset in range(0,100,10):
url = 'https://maoyan.com/board/4?offset='+str(offset)
html = get_one_page(url)
for item in parse_one_page(html):
print(item)
if __name__ == '__main__':
main()
运行截图：
image.png
