spiderComments.py
3.49 KB
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
import time
import requests
import csv
import os
from datetime import datetime
def init():
if not os.path.exists('./articleComments.csv'):
with open('./articleComments.csv','w',encoding='utf-8',newline='') as csvFile:
writer = csv.writer(csvFile)
writer.writerow([
'articleId',
'created_at',
'likes_counts',
'region',
'content',
'authorName',
'authorGender',
'authorAddress',
'authorAvatar'
])
def writerRow(row):
with open('./articleComments.csv', 'a', encoding='utf-8', newline='') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(row)
def get_data(url,params):
headers = {
'Cookie':'SINAGLOBAL=2555941826014.1074.1676801766625; ULV=1719829459275:6:1:2:4660996305989.918.1719827559898:1719743122299; UOR=,,www.baidu.com; XSRF-TOKEN=VtLXviYSIs8lor7sz4iGyigL; SUB=_2A25LhvU9DeRhGeFH6FIX-S3MyD2IHXVo-gj1rDV8PUJbkNAGLRXMkW1Ne2nhI3Gle25QJK0Z99J3trq_NZn6YKJ-; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WW3Mv8V5EupQbbKh.vaZIwU5JpX5KzhUgL.FoM4e05c1Ke7e022dJLoIp7LxKML1KBLBKnLxKqL1hnLBoM41hz41hqReKqN; WBPSESS=Dt2hbAUaXfkVprjyrAZT_LRaDLsnxG-kIbeYwnBb5OUKZiwfVr_UrcYfWuqG-4ZVDM5HeU3HXkDNK_thfRfdS9Ao6ezT30jDksv-CpaVmlTAqGUHjJ7PYkH5aCK4HLxmRq14ZalmQNwzfWMPa4y0VNRLuYdg7L1s49ymNq_5v5vusoz0r4ki6u-MHGraF0fbUTgX14x0kHayEwOoxfLI-w==; SCF=AqmJWo31oFV5itnRgWNU1-wHQTL6PmkBLf3gDuqpdqAIfaWguDTMre6Oxjf5Uzs74JAh2r0DdV1sJ1g6m-wJ5NQ.; _s_tentry=-; Apache=4660996305989.918.1719827559898; PC_TOKEN=7955a7ab1f; appkey=; geetest_token=602cd4e3a7ed1898808f8adfe1a2048b; ALF=1722421868',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:127.0) Gecko/20100101 Firefox/127.0'
}
response = requests.get(url,headers=headers,params=params)
if response.status_code == 200:
return response.json()['data']
else:
return None
def getAllArticleList():
artileList = []
with open('./articleData.csv','r',encoding='utf-8') as reader:
readerCsv = csv.reader(reader)
next(reader)
for nav in readerCsv:
artileList.append(nav)
return artileList
def parse_json(response,artileId):
for comment in response:
created_at = datetime.strptime(comment['created_at'],'%a %b %d %H:%M:%S %z %Y').strftime('%Y-%m-%d')
likes_counts = comment['like_counts']
try:
region = comment['source'].replace('来自', '')
except:
region = '无'
content = comment['text_raw']
authorName = comment['user']['screen_name']
authorGender = comment['user']['gender']
authorAddress = comment['user']['location']
authorAvatar = comment['user']['avatar_large']
writerRow([
artileId,
created_at,
likes_counts,
region,
content,
authorName,
authorGender,
authorAddress,
authorAvatar
])
def start():
commentUrl = 'https://weibo.com/ajax/statuses/buildComments'
init()
articleList = getAllArticleList()
for article in articleList:
articleId = article[0]
print('正在爬取id值为%s的文章评论' % articleId)
time.sleep(2)
params = {
'id':int(articleId),
'is_show_bulletin':2
}
response = get_data(commentUrl,params)
parse_json(response,articleId)
if __name__ == '__main__':
start()