python之爬取猫眼电影TOP100

# -*- coding:utf-8 -*-
import requests
import re
import json


def get_one_page(url):
    try:
        respone = requests.get(url)
        if respone.status_code == 200:
            return respone.text
        return None
    except Exception:
        return None

def write_to_file(conetxt):
    with open('result.txt', 'a') as f:
        f.write(json.dumps(conetxt,ensure_ascii=False) + '\n')
        f.close()




def parse_one_page(html):
    # print(html)
    pattern = re.compile('
.*?board-index.*?>(\d+).*?data-src="(.*?)".*?name">                         +'.*?>(.*?).*?star">(.*?)
.*?releasetime">(.*?)
'
                         +'.*?integer">(.*?).*?fraction">(.*?).*?
', re.S)
    # pattern = re.compile(".*
(.*?)
.*", re.S)
    # items = re.findall(pattern, html)
    # print type(items), len(items)
    # print(items[0])
    items = re.findall(pattern,html)
    # print(items[0])
    for item in items:
        yield {
            "index":item[0].encode("utf-8"),
            "image":item[1].encode("utf-8"),
            "title":item[2].encode("utf-8"),
            "actor":item[3].strip()[3:].encode("utf-8"),
            "time":item[4].strip()[5:].encode("utf-8"),
            "socre":item[5].encode("utf-8")+item[6].encode("utf-8")

        }
    # for i in items:
    #     for j in i:
    #         print(j)

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(i*10)

代码示例，使用2.7版本。注意字节码，在list中之输出ascii码，需要使用json格式将其输出改为utf-8

在yield追加encode编码格式