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)
剛開(kāi)始正則匹配的時(shí)候，最好能夠一小段一小段的匹配，與網(wǎng)頁(yè)源代碼對(duì)照，提取自己需要的內(nèi)容。代碼排版較亂，直接復(fù)制過(guò)去是無(wú)法成功的。
僅供參考
