Requests+正则表达式爬取猫眼电影top100
#!/usr/bin/python#coding=utf-8#import requestsfrom requests.exceptions import RequestExceptionimport reimport jsonfrom multiprocessing import Pooldef get_one_page(url):try:resp
·
#!/usr/bin/python
#coding=utf-8
#
import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool
def get_one_page(url):
try:
response = requests.get(url)
if response.status_code == 200:
return response.text
return None
except RequestException:
return None
pass
def parse_one_page(html):
pattern = re.compile('<dd>.*?>(\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]
}
pass
def write_to_file(content):
with open('result.txt', 'a', encoding = 'utf-8') as f:
f.write(json.dumps(content, ensure_ascii=False) + '\n')
pass
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)
pass
if __name__ == '__main__':
pool = Pool(processes=2)
pool.map(main, [i*10 for i in range(10)])
CSDN联合极客时间，共同打造面向开发者的精品内容学习社区，助力成长！
更多推荐
0
0- 0
已为社区贡献5条内容
所有评论(0)