forked from doocs/leetcode
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathspider.py
197 lines (182 loc) · 9.37 KB
/
spider.py
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
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
import json
import re
import time
from typing import List
from urllib.parse import quote
import requests
import urllib3
urllib3.disable_warnings()
user_agent = (
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/77.0.3865.120 Safari/537.36'
)
sub_folders = [
str(i * 100).zfill(4) + '-' + str(i * 100 + 99).zfill(4) for i in range(100)
]
cn_graph_url = 'https://leetcode-cn.com/graphql'
difficulty = dict(Easy='简单', Medium='中等', Hard='困难')
class Spider:
def __init__(self, cookie_cn: str, cookie_en: str):
self.cookie_cn = cookie_cn
self.cookie_en = cookie_en
self.session = requests.session()
def get_all_questions(self) -> List:
"""获取所有题目"""
headers = {
'accept': 'application/json, text/javascript, */*; q=0.01',
'content-type': 'application/json',
'user-agent': user_agent,
'x-requested-with': 'XMLHttpRequest',
'cookie': self.cookie_en,
}
resp = self.session.get(
url='https://leetcode.com/api/problems/all/',
headers=headers,
allow_redirects=False,
timeout=10,
verify=False,
)
return resp.json()['stat_status_pairs']
def _get_question_detail(self, question_title_slug) -> dict:
"""获取题目详情"""
form_data = {
'operationName': 'globalData',
'query': 'query globalData {\n feature {\n questionTranslation\n subscription\n signUp\n '
'discuss\n mockInterview\n contest\n store\n book\n chinaProblemDiscuss\n '
'socialProviders\n studentFooter\n cnJobs\n enableLsp\n enableWs\n '
'enableDebugger\n enableDebuggerAdmin\n enableDarkMode\n tasks\n '
'leetbook\n __typename\n }\n userStatus {\n isSignedIn\n isAdmin\n '
'isStaff\n isSuperuser\n isTranslator\n isPremium\n isVerified\n '
'isPhoneVerified\n isWechatVerified\n checkedInToday\n username\n '
'realName\n userSlug\n groups\n avatar\n optedIn\n '
'requestRegion\n region\n activeSessionId\n permissions\n notificationStatus {\n '
'lastModified\n numUnread\n __typename\n }\n completedFeatureGuides\n '
'useTranslation\n accountStatus {\n isFrozen\n inactiveAfter\n __typename\n '
'}\n __typename\n }\n siteRegion\n chinaHost\n websocketUrl\n userBannedInfo {\n '
'bannedData {\n endAt\n bannedType\n __typename\n }\n __typename\n }\n}\n',
'variables': {},
}
headers = {
'User-Agent': user_agent,
'Connection': 'keep-alive',
'Content-Type': 'application/json',
'Referer': 'https://leetcode-cn.com/problems/' + question_title_slug,
'cookie': self.cookie_cn,
}
self.session.post(
url=cn_graph_url,
data=json.dumps(form_data),
headers=headers,
timeout=10,
verify=False,
)
form_data = {
'operationName': 'questionData',
'variables': {'titleSlug': question_title_slug},
'query': 'query questionData($titleSlug: String!) {\n question(titleSlug: $titleSlug) {\n '
'questionId\n questionFrontendId\n categoryTitle\n boundTopicId\n title\n '
'titleSlug\n content\n translatedTitle\n translatedContent\n isPaidOnly\n '
'difficulty\n likes\n dislikes\n isLiked\n similarQuestions\n '
'contributors {\n username\n profileUrl\n avatarUrl\n __typename\n '
'}\n langToValidPlayground\n topicTags {\n name\n slug\n '
'translatedName\n __typename\n }\n companyTagStats\n codeSnippets {\n '
'lang\n langSlug\n code\n __typename\n }\n stats\n hints\n '
'solution {\n id\n canSeeDetail\n __typename\n }\n status\n '
'sampleTestCase\n metaData\n judgerAvailable\n judgeType\n mysqlSchemas\n '
'enableRunCode\n envInfo\n book {\n id\n bookName\n pressName\n '
'source\n shortDescription\n fullDescription\n bookImgUrl\n '
'pressImgUrl\n productUrl\n __typename\n }\n isSubscribed\n '
'isDailyQuestion\n dailyRecordStatus\n editorType\n ugcQuestionId\n style\n '
'exampleTestcases\n __typename\n }\n}\n',
}
# get question detail
resp = self.session.post(
url=cn_graph_url,
data=json.dumps(form_data).encode('utf-8'),
headers=headers,
timeout=10,
verify=False,
)
res = resp.json()
return res['data']['question']
def get_question_detail(self, question_title_slug, retry_times=0):
time.sleep(0.5)
for i in range(retry_times + 1):
try:
question_detail = self._get_question_detail(question_title_slug)
if question_detail:
return question_detail
except Exception as e:
print(f'error:{str(e)}')
time.sleep(2)
return None
def handle(self, question: dict) -> dict:
question_title_slug = question['stat']['question__title_slug']
question_detail = self.get_question_detail(question_title_slug, retry_times=5)
if not question_detail:
return {}
url_cn = f'https://leetcode-cn.com/problems/{question_title_slug}'
url_en = f'https://leetcode.com/problems/{question_title_slug}'
frontend_question_id = str(question['stat']['frontend_question_id']).zfill(4)
no = int(frontend_question_id) // 100
question_title_en = question['stat']['question__title']
question_title_en = re.sub(r'[\\/:*?"<>|]', '', question_title_en).strip()
path_cn = f'/solution/{sub_folders[no]}/{frontend_question_id}.{quote(question_title_en)}/README.md'
path_en = f'/solution/{sub_folders[no]}/{frontend_question_id}.{quote(question_title_en)}/README_EN.md'
print(f'{frontend_question_id}. {question_title_en}')
topic_tags = question_detail.get('topicTags')
item = {
'sub_folder': sub_folders[no],
'question_id': str(question['stat']['question_id']).zfill(4),
'frontend_question_id': frontend_question_id,
'paid_only': question['paid_only'],
'paid_only_cn': question_detail.get('isPaidOnly'),
# Shell Database Algorithms Concurrency
'category': question_detail.get('categoryTitle'),
'url_cn': url_cn,
'url_en': url_en,
'relative_path_cn': path_cn,
'relative_path_en': path_en,
'title_cn': question_detail.get('translatedTitle')
or question_title_en
or '',
'title_en': question_title_en or '',
'question_title_slug': question_title_slug,
'content_en': question_detail.get('content'),
'content_cn': question_detail.get('translatedContent')
or question_detail.get('content'),
'tags_en': [e['name'] for e in topic_tags if e['name']] or [],
'tags_cn': [e['translatedName'] for e in topic_tags if e['translatedName']]
or [],
'difficulty_en': question_detail.get('difficulty'),
'difficulty_cn': difficulty.get(question_detail.get('difficulty')),
'code_snippets': question_detail.get('codeSnippets') or [],
}
col1_cn = f'[{frontend_question_id}]({url_cn})'
col2_cn = (
f'[{item["title_cn"]}]({path_cn})'
if item["title_cn"]
else f'[{item["title_en"]}]({path_en})'
)
col3_cn = ','.join([f'`{tag}`' for tag in item['tags_cn']])
col3_cn = '' if (col3_cn == 'None' or not col3_cn) else col3_cn
col4_cn = item['difficulty_cn']
col5_cn = '🔒' if item['paid_only_cn'] else ''
col1_en = f'[{frontend_question_id}]({url_en})'
col2_en = f'[{item["title_en"]}]({path_en})'
col3_en = ','.join([f'`{tag}`' for tag in item['tags_en']])
col3_en = '' if (col3_en == 'None' or not col3_en) else col3_en
col4_en = item['difficulty_en']
col5_en = '🔒' if item['paid_only'] else ''
item['md_table_row_cn'] = [col1_cn, col2_cn, col3_cn, col4_cn, col5_cn]
item['md_table_row_en'] = [col1_en, col2_en, col3_en, col4_en, col5_en]
return item
def run(self):
questions = self.get_all_questions()
details = [self.handle(question) for question in questions]
failed_questions = [
question for i, question in enumerate(questions) if not details[i]
]
details += [self.handle(question) for question in failed_questions]
details = [detail for detail in details if detail]
return details