Update code style
This commit is contained in:
parent
c1cbfd5f79
commit
99844005d6
59
get.py
59
get.py
|
@ -1,13 +1,16 @@
|
|||
#!/usr/bin/python3
|
||||
|
||||
import requests
|
||||
from http.cookiejar import LWPCookieJar
|
||||
"""Download shelves from goodreads."""
|
||||
|
||||
import os
|
||||
import re
|
||||
import lxml.html
|
||||
from http.cookiejar import LWPCookieJar
|
||||
from random import shuffle
|
||||
from time import sleep
|
||||
|
||||
import lxml.html
|
||||
import requests
|
||||
|
||||
re_recommend = re.compile(
|
||||
' <a class="actionLinkLite " href="(/recommendations/([^/]*?)/([^/]*?))">'
|
||||
)
|
||||
|
@ -20,10 +23,11 @@ cookie_file = os.path.join(cookie_dir, "goodreads")
|
|||
cj = LWPCookieJar(cookie_file)
|
||||
if os.path.exists(cookie_file):
|
||||
cj.load()
|
||||
s.cookies = cj
|
||||
s.cookies = cj # type: ignore
|
||||
|
||||
|
||||
def login():
|
||||
def login() -> None:
|
||||
"""Login."""
|
||||
sign_in_page = "https://www.goodreads.com/user/sign_in"
|
||||
page = s.get(sign_in_page).text
|
||||
open("sign_in.html", "w").write(page)
|
||||
|
@ -33,9 +37,12 @@ def login():
|
|||
re_token = re.compile(
|
||||
'<input type="hidden" name="authenticity_token" value="([^"]*?)" />'
|
||||
)
|
||||
re_n = re.compile("<input name='n' type='hidden' value='(\d+)'>")
|
||||
re_n = re.compile(r"<input name='n' type='hidden' value='(\d+)'>")
|
||||
m_n = re_n.search(page)
|
||||
m_token = re_token.search(page)
|
||||
|
||||
token = re_token.search(page).group(1)
|
||||
assert m_token and m_n
|
||||
token = m_token.group(1)
|
||||
|
||||
data = {
|
||||
"utf8": "\u2713",
|
||||
|
@ -44,7 +51,7 @@ def login():
|
|||
"user[password]": "8V8~9:3~U!Ly",
|
||||
"remember_me": 1,
|
||||
"next": "Sign in",
|
||||
"n": re_n.search(page).group(1),
|
||||
"n": m_n.group(1),
|
||||
}
|
||||
|
||||
print(token)
|
||||
|
@ -62,7 +69,8 @@ def login():
|
|||
cj.save(ignore_discard=True)
|
||||
|
||||
|
||||
def get_index():
|
||||
def get_index() -> None:
|
||||
"""Get index."""
|
||||
# url = 'https://www.goodreads.com/recommendations'
|
||||
url = "https://www.goodreads.com/recommendations/?recs_current_view=list"
|
||||
|
||||
|
@ -71,6 +79,7 @@ def get_index():
|
|||
|
||||
|
||||
def get_individual():
|
||||
"""Get individual page."""
|
||||
for line in open("recommendations.html"):
|
||||
if "actionLinkLite" not in line:
|
||||
continue
|
||||
|
@ -79,19 +88,25 @@ def get_individual():
|
|||
yield m.groups()
|
||||
|
||||
|
||||
# art = 'https://www.goodreads.com/recommendations/genre/art'
|
||||
login()
|
||||
get_index()
|
||||
recommend_list = list(get_individual())
|
||||
shuffle(recommend_list)
|
||||
def main() -> None:
|
||||
"""Login and download shelves."""
|
||||
# art = 'https://www.goodreads.com/recommendations/genre/art'
|
||||
login()
|
||||
get_index()
|
||||
recommend_list = list(get_individual())
|
||||
shuffle(recommend_list)
|
||||
|
||||
headers = {"Accept": "text/html"}
|
||||
headers = {"Accept": "text/html"}
|
||||
|
||||
for a, b, c in recommend_list:
|
||||
print((b, c))
|
||||
url = "https://www.goodreads.com" + a
|
||||
for a, b, c in recommend_list:
|
||||
print((b, c))
|
||||
url = "https://www.goodreads.com" + a
|
||||
|
||||
r = s.get(url, headers=headers)
|
||||
filename = os.path.join(b, c + ".html")
|
||||
open(filename, "w").write(r.text)
|
||||
sleep(0.5)
|
||||
r = s.get(url, headers=headers)
|
||||
filename = os.path.join(b, c + ".html")
|
||||
open(filename, "w").write(r.text)
|
||||
sleep(0.5)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
|
Loading…
Reference in a new issue