import json
import requests
import re
import time
from requests.exceptions import RequestException
def get_one_page(url):
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.117 Safari/537.36'
}
response = requests.get(url,headers=headers)
if response.status_code == 200:
return response.text
return None
def parse_one_page(html):
pattern = re.compile('.*?board-index.*?>(.*?).*?data-src="(.*?)".*?alt="(.*?)".*?>.*?.*?star.*?>(.*?).*?releasetime.*?>(.*?).*?integer.*?>(.*?).*?fraction.*?>(.*?).*?',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 write_to_file(content):
with open('result.txt','a',encoding='utf-8') as f:
print(type(json.dumps(content)))
f.write(json.dumps(content,ensure_ascii=False)+'\n')
def main(offset):
url = 'http://maoyan.com/board/4?offset=' + str(offset)
html =get_one_page(url)
for item in parse_one_page(html):
print(item)write_to_file(item)
if __name__== '__main__':
for i in range(10):
main(offset=i * 10)
time.sleep(1)
刚开始正则匹配的时候，最好能够一小段一小段的匹配，与网页源代码对照，提取自己需要的内容。代码排版较乱，直接复制过去是无法成功的。
仅供参考
