88
99
1010class Fetch_PullRequests :
11- """
12- Fetches the pull requests of a user in a organization.
13- """
14- def __init__ (self , username , organization , filename ):
15- """
16- :param username: github user
17- :param organization: Organisation name
18- :param filename: filename, it's optional
19- """
20- self .ORG_URL = f"https://github.com/orgs/{ organization }
21- self .URL = f"https://github.com/{ organization }
22- self .organization = organization
23- self .username = username
24- self .filename = filename
25- 26- def _list_of_repositories (self ):
27- """
28- Function lists the repositories of the organisation.
29-
30- Returns
31- -------
32- list
33- lists the repositories
34-
35- """
36- page = requests .get (self .ORG_URL )
37- tree = html .fromstring (page .content )
38- number_of_pages = tree .xpath ('//*[@id="org-repositories"]/div/div/div[2]/div/em/@data-total-pages' )
39- Repositories = []
40- if len (number_of_pages ) == 0 :
41- Repositories .extend (tree .xpath (
42- '//*[contains(concat( " ", @class, " " ), concat( " ", "wb-break-all", " " ))]//*[contains(concat( " ", @class, " " ), concat( " ", "d-inline-block", " " ))]/text()' ))
43- else :
44- for number in range (1 , int (number_of_pages [0 ]) + 1 ):
45- page_ = requests .get (self .ORG_URL + f"?page={ number } )
46- tree = html .fromstring (page_ .content )
47- Repositories .extend (tree .xpath (
48- '//*[contains(concat( " ", @class, " " ), concat( " ", "wb-break-all", " " ))]//*[contains(concat( " ", @class, " " ), concat( " ", "d-inline-block", " " ))]/text()' ))
49- 50- return list (pd .Series (list (set (Repositories ))).str .strip ().values )
51- 52- def _extract_pullrequests (self , repo ):
53- """
54- Function fetches the pull request of a repo.
55-
56- Parameters
57- ----------
58- repo: str
59- repository name
60-
61- Returns
62- -------
63- pandas dataframe
64- dataframe consists of columns - "Title to PR", "Link of PR", "Status(Merged/Closed/Open)"
65-
66- """
67- # initializing the lists to store the title, link and status of the pull request
68- Title = []
69- Link = []
70- Status = []
71- URL = self .URL + f"/{ repo } { self .username }
72- page = requests .get (URL )
73- tree = html .fromstring (page .content )
74- # to determine the number of pages
75- number_of_pages = tree .xpath ('//*[@id="repo-content-pjax-container"]/div/div[6]/div/em/@data-total-pages' )
76- 77- if len (number_of_pages ) == 0 :
78- # Title.extend(tree.xpath('//*[contains(concat( " ", @class, " " ), concat( " ", "markdown-title", " " ))]/text()'))
79- soup = BeautifulSoup (page .text , 'html.parser' )
80- # "Title may contain text in <code> tags. So,to handle it we use beautiful soup.
81- for tag in soup .find_all ('a' , attrs = {'class' : 'markdown-title' }):
82- Title .append (tag .text .strip ())
83- Link .extend (
84- tree .xpath ('//*[contains(concat( " ", @class, " " ), concat( " ", "markdown-title", " " ))]/@href' ))
85- Status .extend (tree .xpath (
86- '//*[contains(concat( " ", @class, " " ), concat( " ", "pl-3", " " ))]/span/@aria-label' ))
87- 88- else :
89- for number in range (1 , int (number_of_pages [0 ]) + 1 ):
90- URL = self .URL + f"/{ repo } { number } { self .username }
91- page = requests .get (URL )
92- tree = html .fromstring (page .content )
93- 94- # Title.extend(tree.xpath('//*[contains(concat( " ", @class, " " ), concat( " ", "markdown-title", " " ))]/text()'))
95- soup = BeautifulSoup (page .text , 'html.parser' )
96- # Names = tree.xpath(
97- # '//*[contains(concat( " ", @class, " " ), concat( " ", "opened-by", " " ))]//*[contains(concat( " ", @class, " " ), concat( " ", "Link--muted", " " ))]/text()')
98- 99- for tag in soup .find_all ('a' , attrs = {'class' : 'markdown-title' }):
100- Title .append (tag .text .strip ())
101- Link .extend (tree .xpath (
102- '//*[contains(concat( " ", @class, " " ), concat( " ", "markdown-title", " " ))]/@href' ))
103- Status .extend (tree .xpath (
104- '//*[contains(concat( " ", @class, " " ), concat( " ", "pl-3", " " ))]/span/@aria-label' ))
105- 106- Data = {
107- "Title to PR" : Title ,
108- "Link of PR" : Link ,
109- "Status(Merged/Closed/Open)" : Status
110- }
111- 112- # creating a dataframe with the above dictionary
113- dataframe = pd .DataFrame .from_dict (Data )
114- # dataframe.head()
115- 116- # make necessary changes to the columns of dataframe before returning it
117- dataframe ['Status(Merged/Closed/Open)' ] = dataframe ['Status(Merged/Closed/Open)' ].astype (str ).str .replace (
118- " pull request" ,
119- "" , regex = False )
120- if dataframe ['Link of PR' ].dtype != 'O' :
121- dataframe ['Link of PR' ] = dataframe ['Link of PR' ].astype (str )
122- dataframe ['Link of PR' ] = 'https://github.com' + dataframe ['Link of PR' ]
123- 124- return dataframe
125- 126- def get_pullrequests (self ):
127- """
128- Function pass the repo parameter to the "_extract_pullrequests" to fetch the pull requests of the particular repo.
129-
130- Returns
131- -------
132- str
133- return str saying that the file is stored if markdown is not empty.
134-
135- """
136- dataframe = pd .DataFrame ()
137- for repo in self ._list_of_repositories ():
138- dataframe = dataframe .append (self ._extract_pullrequests (repo ), ignore_index = True )
139- 140- markdown = dataframe .to_markdown ()
141- 142- if len (markdown ) > 0 :
143- # creating a markdown file
144- # markdown_file = open(f"{self.filename}.md", "w")
145- with open (f"{ self .filename } , "w" ) as markdown_file :
146- markdown_file .write (markdown )
147- 148- return "Markdown File is successfully stored"
149- 150- return "No pull requests found !!"
11+ """
12+ Fetches the pull requests of a user in a organization.
13+ """
14+ 15+ def __init__ (self , username , organization , filename ):
16+ """
17+ :param username: github user
18+ :param organization: Organisation name
19+ :param filename: filename, it's optional
20+ """
21+ self .ORG_URL = f"https://github.com/orgs/{ organization }
22+ self .URL = f"https://github.com/{ organization }
23+ self .organization = organization
24+ self .username = username
25+ self .filename = filename
26+ 27+ def _list_of_repositories (self ):
28+ """
29+ Function lists the repositories of the organisation.
30+
31+ Returns
32+ -------
33+ list
34+ lists the repositories
35+
36+ """
37+ page = requests .get (self .ORG_URL )
38+ tree = html .fromstring (page .content )
39+ number_of_pages = tree .xpath (
40+ '//*[@id="org-repositories"]/div/div/div[2]/div/em/@data-total-pages' )
41+ Repositories = []
42+ if len (number_of_pages ) == 0 :
43+ Repositories .extend (tree .xpath (
44+ '//*[contains(concat( " ", @class, " " ), concat( " ", "wb-break-all", " " ))]//*[contains(concat( " ", @class, " " ), concat( " ", "d-inline-block", " " ))]/text()' ))
45+ else :
46+ for number in range (1 , int (number_of_pages [0 ]) + 1 ):
47+ page_ = requests .get (self .ORG_URL + f"?page={ number } )
48+ tree = html .fromstring (page_ .content )
49+ Repositories .extend (tree .xpath (
50+ '//*[contains(concat( " ", @class, " " ), concat( " ", "wb-break-all", " " ))]//*[contains(concat( " ", @class, " " ), concat( " ", "d-inline-block", " " ))]/text()' ))
51+ 52+ return list (pd .Series (list (set (Repositories ))).str .strip ().values )
53+ 54+ def _extract_pullrequests (self , repo ):
55+ """
56+ Function fetches the pull request of a repo.
57+
58+ Parameters
59+ ----------
60+ repo: str
61+ repository name
62+
63+ Returns
64+ -------
65+ pandas dataframe
66+ dataframe consists of columns - "Title to PR", "Link of PR", "Status(Merged/Closed/Open)"
67+
68+ """
69+ # initializing the lists to store the title, link and status of the pull request
70+ Title = []
71+ Link = []
72+ Status = []
73+ URL = self .URL + f"/{ repo } { self .username }
74+ page = requests .get (URL )
75+ tree = html .fromstring (page .content )
76+ # to determine the number of pages
77+ number_of_pages = tree .xpath (
78+ '//*[@id="repo-content-pjax-container"]/div/div[6]/div/em/@data-total-pages' )
79+ 80+ if len (number_of_pages ) == 0 :
81+ # Title.extend(tree.xpath('//*[contains(concat( " ", @class, " " ), concat( " ", "markdown-title", " " ))]/text()'))
82+ soup = BeautifulSoup (page .text , 'html.parser' )
83+ # "Title may contain text in <code> tags. So,to handle it we use beautiful soup.
84+ for tag in soup .find_all ('a' , attrs = {'class' : 'markdown-title' }):
85+ Title .append (tag .text .strip ())
86+ Link .extend (
87+ tree .xpath ('//*[contains(concat( " ", @class, " " ), concat( " ", "markdown-title", " " ))]/@href' ))
88+ Status .extend (tree .xpath (
89+ '//*[contains(concat( " ", @class, " " ), concat( " ", "pl-3", " " ))]/span/@aria-label' ))
90+ 91+ else :
92+ for number in range (1 , int (number_of_pages [0 ]) + 1 ):
93+ URL = self .URL + \
94+ f"/{ repo } { number } { self .username }
95+ page = requests .get (URL )
96+ tree = html .fromstring (page .content )
97+ 98+ # Title.extend(tree.xpath('//*[contains(concat( " ", @class, " " ), concat( " ", "markdown-title", " " ))]/text()'))
99+ soup = BeautifulSoup (page .text , 'html.parser' )
100+ # Names = tree.xpath(
101+ # '//*[contains(concat( " ", @class, " " ), concat( " ", "opened-by", " " ))]//*[contains(concat( " ", @class, " " ), concat( " ", "Link--muted", " " ))]/text()')
102+ 103+ for tag in soup .find_all ('a' , attrs = {'class' : 'markdown-title' }):
104+ Title .append (tag .text .strip ())
105+ Link .extend (tree .xpath (
106+ '//*[contains(concat( " ", @class, " " ), concat( " ", "markdown-title", " " ))]/@href' ))
107+ Status .extend (tree .xpath (
108+ '//*[contains(concat( " ", @class, " " ), concat( " ", "pl-3", " " ))]/span/@aria-label' ))
109+ 110+ Data = {
111+ "Title to PR" : Title ,
112+ "Link of PR" : Link ,
113+ "Status(Merged/Closed/Open)" : Status
114+ }
115+ 116+ # creating a dataframe with the above dictionary
117+ dataframe = pd .DataFrame .from_dict (Data )
118+ # dataframe.head()
119+ 120+ # make necessary changes to the columns of dataframe before returning it
121+ dataframe ['Status(Merged/Closed/Open)' ] = dataframe ['Status(Merged/Closed/Open)' ].astype (str ).str .replace (
122+ " pull request" ,
123+ "" , regex = False )
124+ if dataframe ['Link of PR' ].dtype != 'O' :
125+ dataframe ['Link of PR' ] = dataframe ['Link of PR' ].astype (str )
126+ dataframe ['Link of PR' ] = 'https://github.com' + \
127+ dataframe ['Link of PR' ]
128+ 129+ return dataframe
130+ 131+ def get_pullrequests (self ):
132+ """
133+ Function pass the repo parameter to the "_extract_pullrequests" to fetch the pull requests of the particular repo.
134+
135+ Returns
136+ -------
137+ str
138+ return str saying that the file is stored if markdown is not empty.
139+
140+ """
141+ dataframe = pd .DataFrame ()
142+ for repo in self ._list_of_repositories ():
143+ dataframe = dataframe .append (
144+ self ._extract_pullrequests (repo ), ignore_index = True )
145+ 146+ markdown = dataframe .to_markdown ()
147+ 148+ if len (markdown ) > 0 :
149+ # creating a markdown file
150+ # markdown_file = open(f"{self.filename}.md", "w")
151+ with open (f"{ self .filename } , "w" ) as markdown_file :
152+ markdown_file .write (markdown )
153+ 154+ return "Markdown File is successfully stored"
155+ 156+ return "No pull requests found !!"
151157
152158
153159if __name__ == "__main__" :
154- parser = argparse .ArgumentParser ()
155- parser .add_argument ("-u" , "--username" , action = "store_true" )
156- parser .add_argument ("user" , type = str , help = "The name of the user to get the pull requests" )
157- parser .add_argument ("-o" , "--organization" , action = "store_true" )
158- parser .add_argument ("organization_name" , type = str , help = "the organisation where user made the pull requests" )
159- parser .add_argument ("-f" , "--file" , nargs = "?" )
160- parser .add_argument ("filename" , type = str , nargs = "?" , help = "filename to store the markdown table" )
161- args = parser .parse_args ()
162- if args .filename :
163- file_name = args .filename
164- else :
165- file_name = "Markdown_file"
166- if args .username and args .organization :
167- response = Fetch_PullRequests (args .user , args .organization_name , file_name )
168- print (response .get_pullrequests ())
169- else :
170- print ("Please pass atleast two arguments: '--username', '--organisation'" )
160+ parser = argparse .ArgumentParser ()
161+ parser .add_argument ("-u" , "--username" , action = "store_true" )
162+ parser .add_argument (
163+ "user" , type = str , help = "The name of the user to get the pull requests" )
164+ parser .add_argument ("-o" , "--organization" , action = "store_true" )
165+ parser .add_argument ("organization_name" , type = str ,
166+ help = "the organisation where user made the pull requests" )
167+ parser .add_argument ("-f" , "--file" , nargs = "?" )
168+ parser .add_argument ("filename" , type = str , nargs = "?" ,
169+ help = "filename to store the markdown table" )
170+ args = parser .parse_args ()
171+ if args .filename :
172+ file_name = args .filename
173+ else :
174+ file_name = "Markdown_file"
175+ if args .username and args .organization :
176+ response = Fetch_PullRequests (
177+ args .user , args .organization_name , file_name )
178+ print (response .get_pullrequests ())
179+ else :
180+ print ("Please pass atleast two arguments: '--username', '--organisation'" )
0 commit comments