python爬虫练习代码--猫眼电影

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
import requests
import re
from requests.exceptions import RequestException
import json
def get_one_page(url):
try:
response = requests.get(url)
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))
f.write('\n')
f.close()
def main(offset):
url = 'http://maoyan.com/board/4?offset=' + str(offset)
html = get_one_page(url)
#print(html)
for item in parse_one_page(html):
print(item)
write_to_file(item)
if __name__ == '__main__':
for i in range(10):
main(i*10)

  附:
1.正则表达式介绍
2.(译)Python关键字yield的解释(stackoverflow)
3.彻底理解Python中的yield
4.python re 模块 findall 函数用法简述