python猫眼映画採点
1720 ワード
ダイレクトコード
import datetime
import json
from multiprocessing.dummy import Pool
from time import localtime, strftime
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
else:
return None
except RequestException:
return None
def parse_one_page(html):
pattern = re.compile('.*?board-index.*?>(\d+).*?data-src="(.*?)".*?name">(.*?).*?star">(.*?).*?releasetime">(.*?).*?integer">(.*?).*?fraction">(.*?).*? ', re.S)
items = re.findall(pattern, html)
# print(items)
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:
f.write(json.dumps(content, ensure_ascii=False) + '\r')
f.close()
def main(offset):
url = 'https://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(i*10)
start = datetime.datetime.now()
pool = Pool()
pool.map(main, [i*10 for i in range(10)])
end = datetime.datetime.now()
print(end - start)