You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
61 lines
1.8 KiB
61 lines
1.8 KiB
6 months ago
|
import requests
|
||
|
|
import json
|
||
|
|
from lxml import etree
|
||
|
|
import js2py
|
||
|
|
import login
|
||
|
|
USERNAME="td188310339"
|
||
|
|
PASSWORD="Aa123456"
|
||
|
|
COOKIE=login(USERNAME,PASSWORD)
|
||
|
|
HEADERS={
|
||
|
|
'Cookies':COOKIE
|
||
|
|
}
|
||
|
|
BASE_URL='https://www.tadu.com/'
|
||
|
|
def get_id(num):
|
||
|
|
text =requests.get(f'{BASE_URL}/book/988681/{num+1}/?isfirstpart=true',headers=HEADERS).text
|
||
|
|
html=etree.HTML(text)
|
||
|
|
return html.xpath('//a[@id="paging_left"]/@href')[0].strip().split('/')[-1]
|
||
|
|
for chapter_num in range (1,101):
|
||
|
|
js_code = """
|
||
|
|
function encipher(e) {
|
||
|
|
var a = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
|
||
|
|
, t = "="
|
||
|
|
, o = function(e) {
|
||
|
|
var o, s = "", i = e.length;
|
||
|
|
for (o = 0; i - 2 > o; o += 3)
|
||
|
|
s += a[e.charCodeAt(o) >> 2],
|
||
|
|
s += a[((3 & e.charCodeAt(o)) << 4) + (e.charCodeAt(o + 1) >> 4)],
|
||
|
|
s += a[((15 & e.charCodeAt(o + 1)) << 2) + (e.charCodeAt(o + 2) >> 6)],
|
||
|
|
s += a[63 & e.charCodeAt(o + 2)];
|
||
|
|
return i % 3 && (o = i - i % 3,
|
||
|
|
s += a[e.charCodeAt(o) >> 2],
|
||
|
|
i % 3 == 2 ? (s += a[((3 & e.charCodeAt(o)) << 4) + (e.charCodeAt(o + 1) >> 4)],
|
||
|
|
s += a[(15 & e.charCodeAt(o + 1)) << 2],
|
||
|
|
s += t) : (s += a[(3 & e.charCodeAt(o)) << 4],
|
||
|
|
s += t + t)),
|
||
|
|
s
|
||
|
|
};
|
||
|
|
return o(e)
|
||
|
|
}
|
||
|
|
"""
|
||
|
|
encipher = js2py.eval_js(js_code)
|
||
|
|
|
||
|
|
chapter_id = get_id(1)
|
||
|
|
|
||
|
|
dataLimit = encipher(chapter_id)
|
||
|
|
|
||
|
|
print(dataLimit)
|
||
|
|
|
||
|
|
res = requests.get(f'{BASE_URL}getPartContentByCodeTable/988681/{chapter_num},headers=HEADERS)')
|
||
|
|
|
||
|
|
text = res.text
|
||
|
|
|
||
|
|
text = json.loads(text)
|
||
|
|
|
||
|
|
text = text['data']['content']
|
||
|
|
|
||
|
|
html = etree.HTML(text)
|
||
|
|
|
||
|
|
texts = html.xpath(f'//p[not(constains(@data-limit,"{dataLimit}"))]/text()')
|
||
|
|
|
||
|
|
for txt in texts:
|
||
|
|
print(txt)
|