利用python中的request和正则表达式爬取猫眼电影Top100

@TOCpython正则表达式爬取猫眼电影Top100

话不多说直接撸代码

import requests
import re
import json


def get_one_page(url):
	response = requests.get(url)
	try:
		response.raise_for_status()
		response.encoding = response.apparent_encoding
		return response.text
	except:
		return "产生异常"


def parse_one_page(html):
	parttern = re.compile('
.*?board-index.*?>(.*?).*?data-src="(.*?)".*?'
						  '(.*?).*?star">(.*?)
.*?releasetime">(.*?)
.*?'
						  'integer">(.*?).*?fraction">(.*?).*?
',re.S)
	items = re.findall(parttern,html)
	for item in items:
		yield {
			'index':item[0],
			'title':item[2],
			'actor':item[3].strip()[3:],
			'time':item[4].strip()[5:],
			'score':item[5]+item[6],
			'image': item[1]
		}


def write_to_file(content):
	with open('top.txt', 'a', encoding='utf-8') as f:
		f.write(json.dumps(content, ensure_ascii=False)+'\n')
		f.close()


def main(offset):
	url = 'https://maoyan.com/board/4?offset='+str(offset)
	html = get_one_page(url)
	for item in parse_one_page(html):
		write_to_file(item)


if __name__ == '__main__':
	for i in range(10):
		main(i*10)

代码运行结果：