爬猫眼电影
本帖最后由 白白白白丶白 于 2020-11-2 10:46 编辑import json
import requests
from requests.exceptions import RequestException
import re
import time
def get_one_page(url):
try:
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/65.0.3325.162 Safari/537.36',
'Accept-Language': 'zh-CN,zh;q=0.9',
}
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('<dd>.*?board-index.*?>(\d+)</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,
'title': item
}
def write_to_file(content):
with open('result.txt', 'a', encoding='utf-8') as f:
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)
请问这段代码爬猫眼电影的时候为什么时好时坏?
为什么把最后一行的time.sleep(1)去掉就正常了,
可能是你的网络问题,我这边测试正常 EthanHsiung 发表于 2020-11-2 12:36
可能是你的网络问题,我这边测试正常
我这边把 time.sleep删除就正常了,但是加上就时好时坏,不知道什么原因
页:
[1]