Crawler:基于requests库+json库+40行代码实现爬取猫眼榜单TOP100榜电影名称主要信息
Crawler:基于requests库+json库+40行代码实现爬取猫眼榜单TOP100榜电影名称主要信息
输出结果
实现代码
# -*- coding: utf-8 -*-
#Py之Crawler:实实在在的40行代码爬取猫眼榜单TOP100榜电影名称主要信息——Jason niu
import requests
import re
import json
from requests.exceptions import RequestException
from multiprocessing.dummy import Pool
headers = {'User-Agent':'Mozilla/5.0 '}
def get_one_page(url):
try:
res = requests.get(url,headers = headers)
if res.status_code == 200:
return res.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[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) + '\n')
f.close()
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__':
p = Pool()
p.map(main,[i*10 for i in range(10)])
赞 (0)