本文最后更新于 2024年5月6日 早上
Requests类库： https://requests.readthedocs.io/en/latest/user/quickstart/
1
2
3
4
5
6
7
8
| url = 'https://httpbin.org/get'
cookies = dict(do_main="cookies")
response = request.get(url, params="?a=10&b=20", cookies=cookies)
print("content",response.content)
print("cookies", response.cookies)
print("JSON", response.json())
|
1
2
3
4
5
6
7
8
9
10
11
12
| url = 'https://httpbin.org/post'
cookies = dict(do_main="cookies")
data = {"key": "value"}
response = requests.post(url, data=data, cookies=cookies)
print("content",response.content)
print("cookies", response.cookies)
print("JSON", response.json())
|
1
2
3
4
5
6
7
8
9
10
| url = 'https://httpbin.org/delete'
cookies = dict(do_main="cookies")
data = {"key": "value"}
response = requests.delete(url, data=data, cookies=cookies)
print("content",response.content)
print("cookies", response.cookies)
print("JSON", response.json())
|
1
2
3
4
5
6
7
8
9
10
| url = 'https://httpbin.org/delete'
cookies = dict(do_main="cookies")
data = {"key": "value"}
response = requests.put(url, data=data, cookies=cookies)
print("content",response.content)
print("cookies", response.cookies)
print("JSON", response.json())
|
下面我们举例说明
当当网 top500
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 json
import requests
import re
def request_dandan(url):
try:
response = requests.get(url)
print(response.content)
if response.status_code == 200:
return response.text
except requests.RequestException:
return None
def parse_result(html):
pattern = re.compile('<li>.*?list_num.*?(\d+).</div>.*?<img src="(.*?)".*?class="name".*?title="(.*?)">.*?class="star">.*?class="tuijian">(.*?)</span>.*?class="publisher_info">.*?target="_blank">(.*?)</a>.*?class="biaosheng">.*?<span>(.*?)</span></div>.*?<p><span\sclass="price_n">¥(.*?)</span>.*?</li>',re.S)
items = re.findall(pattern, html)
for item in items:
write_item_to_file(item)
yield {
'range': item[0],
'iamge': item[1],
'title': item[2],
'recommend': item[3],
'author': item[4],
'times': item[5],
'price': item[6]
}
def write_item_to_file(item):
print('开始写入数据 ====> ' + str(item))
with open('book.txt', 'a', encoding='UTF-8') as f:
f.write(json.dumps(item, ensure_ascii=False) + '\n')
f.close()
def main(page):
url = 'http://bang.dangdang.com/books/fivestars/01.00.00.00.00.00-recent30-0-0-1' + str(page)
html = request_dandan(url)
parse_result(html)
if __name__ == "__main__":
for i in range(1, 26):
main(i)
|