import requests
import json
import re
from requests.exceptions import RequestException
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'
}
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('<li.*?bg.*?title.*?>(.*?)</a>(.*?)</li>')
items = re.findall(pattern, html)
for item in items:
yield {
'locantion': item[0],
'time': item[1]
}
def write_to_file(content):
with open('slw.txt', 'a', encoding='utf-8')as f:
f.write(json.dumps(content, ensure_ascii=False) + '\n')
url = 'http://www.24timemap.com/'
pageHtml = get_one_page(url)
respGenerator = parse_one_page(pageHtml)
for eachItemDict in respGenerator:
write_to_file(eachItemDict)
time.sleep(1)
uj5u.com熱心網友回復：
你就不能認真研究下 python 的代碼縮進要求嗎？uj5u.com熱心網友回復：
謝謝你的建議！！！！我認真去看了！！我的爬蟲又行了
uj5u.com熱心網友回復：
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/78186.html
上一篇：R語言 收捲時出錯: $ operator is invalid for atomic vectors 求大神們指教