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
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
| # 载入相应的模块
import time
import requests
import openpyxl
time1 = time.time()
lists = []
lists.append(['answer_kname','headline','voteup_count','content'])
##################
for i in range(0,1,1):
url = 'https://www.zhihu.com/api/v4/questions/64270965/answers'
headers = {
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
}
params = {
'include': 'data[*].is_normal,admin_closed_comment,reward_info,is_collapsed,annotation_action,annotation_detail,collapse_reason,is_sticky,collapsed_by,suggest_edit,comment_count,can_comment,content,editable_content,voteup_count,reshipment_settings,comment_permission,created_time,updated_time,review_info,relevant_info,question,excerpt,relationship.is_authorized,is_author,voting,is_thanked,is_nothelp,is_labeled,is_recognized,paid_info,paid_info_content;data[*].mark_infos[*].url;data[*].author.follower_count,badge[*].topics',
'offset': str(i),
'limit': '3',
'sort_by': 'default',
'platform': 'desktop'
}
res = requests.get(url, headers=headers, params=params)
res_json = res.json()
items = res_json['data']
for item in items:
answer_kname = item['author']['name']
headline = item['author']['headline']
content = item['content']
voteup_count = item['voteup_count']
lists.append([answer_kname,headline,voteup_count,content])
##################
for i in range(3,3,1):
url = 'https://www.zhihu.com/api/v4/questions/64270965/answers'
headers = {
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
}
params = {
'include': 'data[*].is_normal,admin_closed_comment,reward_info,is_collapsed,annotation_action,annotation_detail,collapse_reason,is_sticky,collapsed_by,suggest_edit,comment_count,can_comment,content,editable_content,voteup_count,reshipment_settings,comment_permission,created_time,updated_time,review_info,relevant_info,question,excerpt,relationship.is_authorized,is_author,voting,is_thanked,is_nothelp,is_labeled,is_recognized,paid_info,paid_info_content;data[*].mark_infos[*].url;data[*].author.follower_count,badge[*].topics',
'offset': str(i),
'limit': '5',
'sort_by': 'default',
'platform': 'desktop'
}
res = requests.get(url, headers=headers, params=params)
res_json = res.json()
items = res_json['data']
for item in items:
answer_kname = item['author']['name']
headline = item['author']['headline']
content = item['content']
voteup_count = item['voteup_count']
lists.append([answer_kname,headline,voteup_count,content])
##################
for i in range(8,278,5):
url = 'https://www.zhihu.com/api/v4/questions/64270965/answers'
headers = {
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
}
params = {
'include': 'data[*].is_normal,admin_closed_comment,reward_info,is_collapsed,annotation_action,annotation_detail,collapse_reason,is_sticky,collapsed_by,suggest_edit,comment_count,can_comment,content,editable_content,voteup_count,reshipment_settings,comment_permission,created_time,updated_time,review_info,relevant_info,question,excerpt,relationship.is_authorized,is_author,voting,is_thanked,is_nothelp,is_labeled,is_recognized,paid_info,paid_info_content;data[*].mark_infos[*].url;data[*].author.follower_count,badge[*].topics',
'offset': str(i),
'limit': '5',
'sort_by': 'default',
'platform': 'desktop'
}
res = requests.get(url, headers=headers, params=params)
res_json = res.json()
items = res_json['data']
for item in items:
answer_kname = item['author']['name']
headline = item['author']['headline']
content = item['content']
voteup_count = item['voteup_count']
lists.append([answer_kname,headline,voteup_count,content])
##################
file = openpyxl.Workbook()
sheet = file.active
sheet.title = 'answers'
for i in lists:
sheet.append(i)
file.save('即将步入研究生，有什么忠告.xlsx')
##################
file_html = open('知乎：即将步入研究生，有什么忠告.html','w',encoding= 'utf-8')
for i in lists:
file_html.write(i[3])
file_html.close()
##################
time2 = time.time()
print('爬虫耗时：%.3f'%(float(time2-time1)),'秒')
|