requests爬取猫眼电影

直接上代码，代码上也有详细的注释：

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

获取每一页的内容

def get_one_page(url):

#写的严谨点用，try....except的方法
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

用正则匹配出自己想要的内容

def parse_one_page(html):
# 正则预先生成用compile方法
pattern = re.compile('

.?board-index.?>(\d+).?data-src="(.?)".?name"> + '.?>(.?).?star">(.?)

.?releasetime">(.?)

'
+ '.?integer">(.?).?fraction">(.?).?

', re.S)
items = re.findall(pattern, html)
for item in items:
# 用生成器返回
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]
}

写到txt中

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)
# 设置时间，防止反爬
time.sleep(1)