爬虫学习：Requests+正则表达式爬取猫眼电影

B站视频av19057145
`P14 requests+正则表达式
爬取网站信息代码：
（之前没有添加header时失败）

import requests
from requests.exceptions import RequestException
def get_one_page(url):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
        }
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None
def main():
    url = 'https://maoyan.com/board/4'
    html = get_one_page(url)
    print(html)
if __name__ == '__main__':
    main()

在简单的对数据进行归纳整理后的代码如下：

import requests
from requests.exceptions import RequestException
import  re
    
def get_one_page(url):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
        }
        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):
    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]
        }
    #print(items)


def main():
    url = 'https://maoyan.com/board/4'
    html = get_one_page(url)
    for item in parse_one_page(html):
        print(item)


if __name__ == '__main__':
    main()

在线程池中创造多进程爬取数据（会出现顺序不一致，初步估计是多进程状态下造成顺序混乱）：

   import requests
    from multiprocessing import Pool
    import json
    from requests.exceptions import RequestException
    import re
    
    
    #获取网页信息
    def get_one_page(url):
        try:
            headers = {
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
            }
            response = requests.get(url, headers=headers)
            if response.status_code == 200:
                return response.text
            return None
        except RequestException:
            return None
    
    
    #抓取网页中需要的信息
    #圆括号中代表我们需要抓取的数据
    #需要熟知re库中compile和findall方法
    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)
    #建立字典结构使其规则输出    [x:]的意思是删除item[y]组中前x个字符
        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]
            }
        #print(items)
    
    
    #写入到文件
    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()
    #主函数
    def main(offset):
        url = 'https://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__':
    
        pool = Pool()
        pool.map(main,[i*10 for i in range(10)])