python初级爬虫之猫眼电影

**

逐步爬取猫眼电影排行信息

**

一、抓取一页，简单地思路

import requests
import re

headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)\
        Chrome/71.0.3578.98 Safari/537.36'
}
r = requests.get('https://maoyan.com/board/4',headers=headers) 
items = re.findall('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
                   + '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                   + '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',r.text,re.S)
print(items)

先使用requests库抓取页面，再使用正则表达式提取页面相关的信息，最后输出结果：

二、整理代码，使其更加简洁和规范，便于分页抓取。

import requests
import re

def get_page(url):
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)\
        Chrome/71.0.3578.98 Safari/537.36'
    }
    response = requests.get(url,headers=headers)
    return response.text

def parse_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)
    return items
   
def main():
    url = 'https://maoyan.com/board/4'
    html = get_page(url)
    results = parse_page(html)
    print(results)
    
main()

上面代自定义函数来规范代码，内容基本不变，输出结果仍为列表型。下面来整理一下输出的结果：

import requests
import re

def get_page(url):
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)\
        Chrome/71.0.3578.98 Safari/537.36'
    }
    response = requests.get(url,headers=headers)
    return response.text

def parse_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)
    return items
    
def main():
    url = 'https://maoyan.com/board/4'
    html = get_page(url)
    for item in parse_page(html):
        print(item[0],item[1],item[2],item[3].strip()[3:],item[4].strip()[5:],item[5] + item[6])
    
main()

三、终极整理，同时完成分页抓取，共抓取前100名，完整代码如下：

import re
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/71.0.3578.98 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]
        }
 
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)

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

小结：一步一步来做，先理解每一个步骤的原理，懂得相关知识点的使用，才可以学到东西。最后的代码中，使用了requests库来抓取页面、re库来完成正则表达式。同时，在输出结果端使用一个生成器来完成迭代，使得输出结果为字典型。