python初探

2020-12-28开始学习python爬虫，在博客园记录一下自己的学习进程
对网页F12的network有了一定的了解，后面看服务器传来的代码在network看
对正则表达式有了初步的利用，对于一般的正则表达式选择去百度，对于爬虫要用的正则表达式，选择了在固定的标签后面加上（.*？）对于后面的字符串进行不贪婪匹配
对基本库的学习：
``

data = bytes(urllib.parse.urlencode({'word' : 'hello'}), encoding='utf-8')
response = urllib.request.urlopen('url') #读取网页
response = urllib.request.urlopen('url', data=data)#提交了data参数
response = urllib.request.urlopen('url', timeout=1)#提交了超时参数timeout

urllib.request.Request(url, data=None, headers={})#更灵活传递参数
request = urllib.request.Request(url)
response = urllib.request.urlopen(request)

抓取猫眼电影前100排行

```
import json
import requests
from requests.exceptions import RequestException
import re
import time


def get_one_page(url):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 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 write_to_file(content):
    with open('result.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')


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(offset=i * 10)
        time.sleep(1)

```