FilesExpand file tree

 master

/

parse_source.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

executable file

·

144 lines (121 loc) · 4.58 KB

 master

/

parse_source.py

Copy path

Top

File metadata and controls

• Code
• Blame

executable file

·

144 lines (121 loc) · 4.58 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

#!/usr/bin/env python3

"""Parse Leetcode/Lintcode html page to markdown."""

import sys

from pyquery import PyQuery

import requests

import html2text

class Code(object):

"""Leetcode/Lintcode base."""

def __init__(self, arg):

"""Init."""

super(Code, self).__init__()

self.arg = arg

self.raw_p_html = None

def get_raw_p_html(self, url):

"""Get raw problem html page."""

self.raw_p_html = PyQuery(url=url)

return self.raw_p_html

def get_p_body(self, raw_p_html):

"""Get problem html body only."""

pass

def get_p_title(self, raw_p_html):

p_title = raw_p_html('title').text().split('|')[0].strip()

return p_title

def get_p_tags(self, raw_p_html):

pass

def get_p_difficulty(self, raw_p_html):

pass

class Lintcode(Code):

def __init__(self):

super(Lintcode, self).__init__()

def get_src_detail(self, src_url):

src_page = self.get_src_page(src_url)

src_detail = {}

problem_detail = src_page('#problem-aside')

# difficulty_level = problem_detail('h4')('.label').text()

title = problem_detail('h4')('a').text().strip()

raw_tags = problem_detail('#tags')('a')

tags = [tag.text for tag in raw_tags]

raw_detail = src_page('#problem-aside')('#description').html()

body_start = raw_detail.find('<p>')

body_end = raw_detail.find('<b>Tags</b>')

raw_body = raw_detail[body_start:body_end]

body = raw_body.replace('<b>', '<h4>')

body = body.replace('</b>', '</h4>')

src_detail['title'] = title

src_detail['tags'] = tags

# src_detail['level'] = difficulty_level

src_detail['body'] = body

return src_detail

class Leetcode(Code):

def __init__(self, arg):

super(Leetcode, self).__init__(arg)

def get_p_body(self, raw_p_html):

"""Get the main content of problem."""

q_content_html = raw_p_html('.question-content').html()

p_body_start = q_content_html.find('<p>')

p_body_end = q_content_html.find('<div>')

p_body = q_content_html[p_body_start:p_body_end]

# body = p_body.replace('<b>', '<h4>')

# body = body.replace('</b>', '</h4>')

return p_body

def get_p_tags(self, raw_p_html):

p_tags = []

try:

raw_tags = raw_p_html('.btn.btn-xs.btn-primary')

for tag in raw_tags:

if tag.attrib['href'].startswith('/tag/'):

p_tags.append(tag.text)

except Exception as err:

print('Error: ', err)

return p_tags

def get_p_difficulty(self, raw_p_html):

return raw_p_html('.question-info.text-info').text().split(' ')[-1]

def main(argv):

if (len(argv) != 2):

print("Usage: python parse_source.py problem_url")

scripts, url = argv

url = url.strip().rstrip('/').replace('/zh-cn/', '/en/')

p_url_name = url.split('/')[-1]

lintcode_site = 'http://www.lintcode.com/en/problem/'

leetcode_site = 'https://leetcode.com/problems/'

p_urls = {}

p_html_inst = Code(url)

h = html2text.HTML2Text()

if url.startswith(lintcode_site):

p_urls['lintcode'] = url

leetcode_url = leetcode_site + p_url_name + '/'

response = requests.head(leetcode_url)

if response.status_code == 200:

p_urls['leetcode'] = leetcode_url

p_html_inst = Lintcode(url)

elif url.startswith(leetcode_site):

p_urls['leetcode'] = url + '/'

lintcode_url = lintcode_site + p_url_name + '/'

response = requests.head(lintcode_url)

if response.status_code == 200:

p_urls['lintcode'] = lintcode_url

p_html_inst = Leetcode(url)

else:

pass

raw_p_html = p_html_inst.get_raw_p_html(url)

p_title = p_html_inst.get_p_title(raw_p_html)

p_body = p_html_inst.get_p_body(raw_p_html)

p_difficulty = p_html_inst.get_p_difficulty(raw_p_html)

raw_p_tags = p_html_inst.get_p_tags(raw_p_html)

raw_p_tags.append(p_difficulty)

lines = []

lines.append('# ' + p_title + '\n')

p_tags = ['TAG_' + tag.replace(' ', '_') for tag in raw_p_tags]

tags = ' '.join(p_tags)

lines.append('**TAGS:** ' + tags + '\n')

lines.append('## Question' + '\n')

# generate leetcode/lintcode source url lists

for key in sorted(p_urls):

p_list = '- ' + key + ': ' + '[' + p_title + '](' + p_urls[key] + ')'

lines.append(p_list)

lines.append('\n### Problem Statement\n')

lines.append(h.handle(p_body))

print('\n'.join(lines))

if __name__ == "__main__":

main(sys.argv)