def fetch_submission(self, slug):
print(f"🤖 Fetching submission for problem: {slug}")
query_params = {
'operationName': "Submissions",
'variables': {"offset": 0, "limit": 20, "lastKey": '', "questionSlug": slug},
'query': '''query Submissions($offset: Int!, $limit: Int!, $lastKey: String, $questionSlug: String!) {
submissionList(offset: $offset, limit: $limit, lastKey: $lastKey, questionSlug: $questionSlug) {
lastKey
hasNext
submissions {
id
statusDisplay
lang
runtime
timestamp
url
isPending
__typename
}
__typename
}
}'''
}
resp = self.session.post("https://leetcode.com/graphql",
data=json.dumps(query_params).encode('utf8'),
headers={
"content-type": "application/json",
})
body = json.loads(resp.content)
# parse data
submissions = get(body, "data.submissionList.submissions")
if len(submissions) > 0:
for sub in submissions:
if Submission.get_or_none(Submission.id == sub['id']) is not None:
continue
if sub['statusDisplay'] == 'Accepted':
url = sub['url']
html = self.session.get(f'https://leetcode.com{url}').text
pattern = re.compile(
r'submissionCode: \'(?P<code>.*)\',\n editCodeUrl', re.S
)
matched = pattern.search(html)
code = matched.groupdict().get('code') if matched else None
if code:
Submission.insert(
id=sub['id'],
slug=slug,
language=sub['lang'],
created=sub['timestamp'],
source=code.encode('utf-8')
).execute()
else:
raise Exception(f"Cannot get submission code for problem: {slug}")
random_wait(10, 15)
def fetch_problem(self, slug, accepted=False):
print(f"🤖 Fetching problem: https://leetcode.com/problem/{slug}/...")
query_params = {
'operationName': "getQuestionDetail",
'variables': {'titleSlug': slug},
'query': '''query getQuestionDetail($titleSlug: String!) {
question(titleSlug: $titleSlug) {
questionId
questionFrontendId
questionTitle
questionTitleSlug
content
difficulty
stats
similarQuestions
categoryTitle
topicTags {
name
slug
}
}
}'''
}
resp = self.session.post(
"https://leetcode.com/graphql",
data=json.dumps(query_params).encode('utf8'),
headers={
"content-type": "application/json",
})
body = json.loads(resp.content)
# parse data
question = get(body, 'data.question')
Problem.replace(
id=question['questionId'], display_id=question['questionFrontendId'], title=question["questionTitle"],
level=question["difficulty"], slug=slug, description=question['content'],
accepted=accepted
).execute()
for item in question['topicTags']:
if Tag.get_or_none(Tag.slug == item['slug']) is None:
Tag.replace(
name=item['name'],
slug=item['slug']
).execute()
ProblemTag.replace(
problem=question['questionId'],
tag=item['slug']
).execute()
random_wait(10, 15)
def slowly_gather():
max_range = 10000
increment = 1
current_start_page = 1 + len(
[f for f in os.listdir('scraping') if '.xlsx' in f]) * increment
while current_start_page < max_range:
print('Start Page %s' % current_start_page)
parser = AllRecipesParser(start_page=current_start_page,
search_limit=increment)
parser.main()
current_start_page += increment
random_wait(60)
def fetch_solution(self, slug):
print(f"🤖 Fetching solution for problem: {slug}")
query_params = {
"operationName": "QuestionNote",
"variables": {"titleSlug": slug},
"query": '''
query QuestionNote($titleSlug: String!) {
question(titleSlug: $titleSlug) {
questionId
article
solution {
id
content
contentTypeId
canSeeDetail
paidOnly
rating {
id
count
average
userRating {
score
__typename
}
__typename
}
__typename
}
__typename
}
}
'''
}
resp = self.session.post("https://leetcode.com/graphql",
data=json.dumps(query_params).encode('utf8'),
headers={
"content-type": "application/json",
})
body = json.loads(resp.content)
# parse data
solution = get(body, "data.question")
if solution['solution']['paidOnly'] is False:
Solution.replace(
problem=solution['questionId'],
url=f"https://leetcode.com/articles/{slug}/",
content=solution['solution']['content']
).execute()
random_wait(10, 15)
def get_urls_to_parse(self):
search_url = self.base_url + '/' + self.base_search_page
pageno = self.start_page
search_page = self.call_function(requests.get,
url=search_url + str(pageno),
headers=HEADERS)
if search_page == 'Error':
return
while search_page != 'Error' and search_page.status_code != 404 and self.search_limit > (
pageno - self.start_page):
if search_page.status_code == 503: # temporary off
random_wait(60)
continue
soup = BeautifulSoup(search_page.content, features='html.parser')
self.parse_search_page(soup)
pageno += 1
random_wait(15)
search_page = self.call_function(requests.get,
url=search_url + str(pageno),
headers=HEADERS)
def collect_articles(self):
local_folder = 'html-downloads' + '\\' + self.base_url.split(
'www')[-1].strip('.')
if not os.path.exists(local_folder):
os.makedirs(local_folder)
for url in self.data:
local_html = local_folder + '\\' + url.replace(
self.base_url, '').strip('/').replace('/', '-') + '.html'
if os.path.exists(local_html):
print("Using Local Copy %s" % url)
with open(local_html, 'rb') as html:
content = html.read()
else:
random_wait(10) # only need to chill when using live
print("Using live copy %s" % url)
resp = self.call_function(requests.get,
url=url,
headers=HEADERS)
if resp == 'Error':
random_wait(20)
continue
if resp.status_code == 404:
print("Cannot find %s" % url)
continue
if resp.status_code == 503:
random_wait(20)
continue
content = resp.content
if not os.path.exists(os.path.dirname(local_html)):
os.makedirs(os.path.dirname(local_html))
with open(local_html, 'wb') as html:
html.write(content)
soup = BeautifulSoup(content)
try:
if soup.contents[
2] == self.alt_flag: # todo implement alt parser
print('Alt flagged', local_html)
continue
info = self.parse_article_page(soup)
except Exception as wow:
print('Serious error with url %s, : %s' % (url, wow))
continue
self.data[url].update(info)
def update_to_goodreads(entries, cookies, disk_cache, limit, wait):
"""Update book entries to Goodreads.
:param entries: list of books
:param cookies: login cookie for Goodreads
:param disk_cache: cache of updated books
"""
session = requests.Session()
success = []
error = []
for entry in entries:
isbn13 = entry['isbn13']
isbns = [isbn13]
try:
isbn10 = pyisbn.convert(isbn13)
isbns.append(isbn10)
except Exception:
pass
resp = check_exists(session, (isbn10, isbn13), cookies)
if not resp:
logging.warning('{} couldn\'t be found'.format(repr_book(entry)))
error.append(entry)
disk_cache[entry['isbn13']] = 'e'
random_wait(2)
continue
url = get_edit_url(resp)
if not url:
logging.warning('{}\' url is not found'.format(repr_book(entry)))
error.append(entry)
disk_cache[entry['isbn13']] = 'e'
random_wait(2)
continue
submit_url, form_data = get_form_data(session, cookies, url)
if not form_data:
logging.warning('{}\' form data is not found'.format(repr_book(
entry)))
error.append(entry)
disk_cache[entry['isbn13']] = 'e'
random_wait(2)
continue
# Do not cause any updates
form_data['review[cog_explicit]'] = '0'
for key in ('add_to_blog', 'add_update'):
if key in form_data:
form_data[key] = '0'
# sanity check
if len([key for key in form_data if 'readingSessionDatePicker' in key
]) != 10:
logging.warning('{}\' date is problematic'.format(repr_book(
entry)))
logging.warning(form_data)
error.append(entry)
disk_cache[entry['isbn13']] = 'e'
continue
if update_book(entry, form_data, submit_url, session, cookies):
success.append(entry)
disk_cache[entry['isbn13']] = ''
else:
error.append(entry)
disk_cache[entry['isbn13']] = 'e'
if limit is not None and len(success) >= limit:
break
random_wait()
return success, error
