爬虫实战1：使用requests和正则爬取电影信息

代码如下

# coding=utf-8
import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool  #引入进程池


def get_one_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/65.0.3325.181 Safari/537.36'
    }
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None


def parse_one_page(html):
    #得到排名，简报，标题，主演,上映时间，分数
    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)

    #对输出内容进行格式化,将原先的元组格式转化为字典
    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]
        }

#json.dumps方法将字典转变为字符串
#encoding和下面的ascii如果不写的话resul.txt文件内容为乱码
def write_to_file(content):
    with open('result.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '
')
        f.close()


#offset用来表示不同页面
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__':
    '''
    抓取top100的影片信息的一般方法，i*10的原因是网址上每页offset是按10的倍数变化的
    for i in range(10):
        main(i*10)
'''
    #使用进程池提高效率
    pool = Pool()
    pool.map(main, [i*10 for i in range(10)])

使用pyquery简单实现

from pyquery import PyQuery as pq

headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'}

def write_to_file(content):
    with open('result.txt', 'a') as f:
        f.write(content)


def main(offset):
    url='http://maoyan.com/board/4?offset=' + str(offset)
    doc=pq(url, headers=headers)

    dd=doc('dd').text()
    for x in dd.split(" "):
        print(x)
        print('
')
        write_to_file(x + '
')

        """
        合些的话可以如下        
        c=''.join([x, '
'])
        print(c)
        """
        
if __name__ == '__main__':
    for i in range(10):
        main(i*10)