python网络爬虫--正则表达式抓取猫眼电影排行TOP100

本篇随笔，记录学习崔庆才老师编著的《Python3 网络爬虫实战开发》

打开猫眼电影，找到TOP100榜，观察URL连接。发现offset字段变化，其它都不变。offset字段即电影数量的偏移量。

# 使用requests第三方请求库
import requests
import re
import json


def get_one_page(url):
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"
        }
    response = requests.get(url,headers = headers)
    if response.status_code == 200:
        return response.text
    return None


def parse_one_page(html):
    pattern = re.compile('<dd>.*?board-index.*?>(.*?)</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].strip(),
            "actor":item[3].strip()[3:] if len(item[3])>3 else "",
            "time":item[4].strip()[5:] if len(item[4])>5 else "",
            "score":item[5].strip() + item[6].strip()
            }

def write_to_file(content):
    with open("result.text","a",encoding = "utf-8") as f:
        print(type(json.dumps(content)))
        f.write(json.dumps(content,ensure_ascii = False)+"\n")      


def main(offset):
    url = "https://maoyan.com/board/4?offset="+str(offset)
    html = get_one_page(url)
    for item in parse_one_page(html):
        write_to_file(item)

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

 

# 使用urllib内置请求库
from urllib import request
import re
import json


def get_one_page(url):
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"
        }
    my_request = request.Request(url,headers = headers)
    response = request.urlopen(my_request)
    if response.code == 200:
        return response.read()
    return None


def parse_one_page(html):
    pattern = re.compile('<dd>.*?board-index.*?>(.*?)</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].strip(),
            "actor":item[3].strip()[3:] if len(item[3])>3 else "",
            "time":item[4].strip()[5:] if len(item[4])>5 else "",
            "score":item[5].strip() + item[6].strip()
            }

def write_to_file(content):
    with open("result.text","a",encoding = "utf-8") as f:
        print(type(json.dumps(content)))
        f.write(json.dumps(content,ensure_ascii = False)+"\n")      


def main(offset):
    url = "https://maoyan.com/board/4?offset="+str(offset)
    html = get_one_page(url)
    for item in parse_one_page(html):
        write_to_file(item)

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