import json
import requests
import re
from requests.exceptions import RequestException
#请求单页
def get_one_page(url):
try:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.79 Safari/537.36'
}
response = requests.get(url,headers=headers)
if response.status_code == 200:
return response.text
return None
except RequestException:
return None
#解析页面
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)
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 main(offset):
url = 'https://maoyan.com/board/4?offset='+str(offset)
html = get_one_page(url)
htmls=parse_one_page(html)
for item in htmls:
print(item)
wirte_to_file(item) #写入文件
#写到文件中
def wirte_to_file(content):
with open('TOP100.txt','a') as f:
f.write(json.dumps(content)+'\n')
f.close()
#开始调用
if __name__ =='__main__':
#普通方式
for item in range(10):
main(str(item*10))