111 lines
2.8 KiB
Python
111 lines
2.8 KiB
Python
|
import requests
|
||
|
|
import json
|
||
|
|
import os
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
from PIL import Image
|
||
|
|
from fpdf import FPDF
|
||
|
|
|
||
|
|
baseurl = "https://bvtlab.com"
|
||
|
|
phpsessid = "lps4od32b4kgibtgd1440df7i5"
|
||
|
|
sid = "b88e922dd251e1f6"
|
||
|
|
time = "6535904988"
|
||
|
|
|
||
|
|
reqcookies = dict(PHPSESSID=phpsessid)
|
||
|
|
|
||
|
|
def getImageName(imageURL):
|
||
|
|
result = ""
|
||
|
|
for char in imageURL:
|
||
|
|
result += char
|
||
|
|
if char == "/":
|
||
|
|
result = ""
|
||
|
|
|
||
|
|
return result
|
||
|
|
|
||
|
|
def downloadImage(imageURL, outDir, outFile):
|
||
|
|
i = requests.get(imageURL)
|
||
|
|
|
||
|
|
if not os.path.exists(outDir):
|
||
|
|
os.makedirs(outDir)
|
||
|
|
|
||
|
|
with open(os.path.join(outDir, outFile), 'wb') as tempFile:
|
||
|
|
tempFile.write(i.content)
|
||
|
|
|
||
|
|
def getSegments():
|
||
|
|
payload = {
|
||
|
|
"action": "getsegments",
|
||
|
|
"sid": sid,
|
||
|
|
}
|
||
|
|
|
||
|
|
r = requests.get(baseurl + "/ebook.php", params=payload, cookies=reqcookies)
|
||
|
|
items = r.json()
|
||
|
|
|
||
|
|
result = []
|
||
|
|
|
||
|
|
for i in range(0, len(items)):
|
||
|
|
if items[i]["Section"] == None:
|
||
|
|
#print(i+1, items[i]["Title"], items[i]["Short_Title"])
|
||
|
|
result.append([i+1, items[i]["Level1"], items[i]["Segment_Depth"], items[i]["Segment_Level"], items[i]["Line_Item"], items[i]["Short_Title"], items[i]["Title"]])
|
||
|
|
|
||
|
|
return result
|
||
|
|
|
||
|
|
def getPages(seg, lev, seg_dep, seg_lev, li):
|
||
|
|
payload = {
|
||
|
|
"action": "getpages",
|
||
|
|
"sid": sid,
|
||
|
|
"segment": seg,
|
||
|
|
"level": lev,
|
||
|
|
"segment_depth": seg_dep,
|
||
|
|
"segment_level": seg_lev,
|
||
|
|
"line_item": li,
|
||
|
|
"width": 550
|
||
|
|
}
|
||
|
|
|
||
|
|
r = requests.get(baseurl + "/ebook.php", params=payload, cookies=reqcookies)
|
||
|
|
soup = BeautifulSoup(r.text, 'html.parser')
|
||
|
|
|
||
|
|
return soup.find_all("div")
|
||
|
|
|
||
|
|
def ripPages(divlist, dir, pdf):
|
||
|
|
for d in divlist:
|
||
|
|
pagenum = d["data-page"]
|
||
|
|
imgs = d.find_all("img")
|
||
|
|
|
||
|
|
print(pagenum, "----", d)
|
||
|
|
|
||
|
|
width = 1100
|
||
|
|
height = 1491
|
||
|
|
|
||
|
|
stichedIm = Image.new('RGB', (width, height))
|
||
|
|
|
||
|
|
ih = 0
|
||
|
|
|
||
|
|
for im in imgs:
|
||
|
|
print(im)
|
||
|
|
imurl = im["data-src"]
|
||
|
|
downloadImage(imurl, dir + "/page_" + pagenum, im["id"] + ".jpg")
|
||
|
|
|
||
|
|
im = Image.open(os.path.join(dir + "/page_" + pagenum, im["id"] + ".jpg"))
|
||
|
|
print(im.size)
|
||
|
|
#height += im.size[1]
|
||
|
|
|
||
|
|
stichedIm.paste(im, (0, im.size[1] * ih))
|
||
|
|
|
||
|
|
ih += 1
|
||
|
|
|
||
|
|
stichedIm.save(dir + "/page_"+ pagenum + ".jpg")
|
||
|
|
pdf.add_page()
|
||
|
|
pdf.image(dir + "/page_"+ pagenum + ".jpg", 0, 0)
|
||
|
|
print("the height:", width, height)
|
||
|
|
|
||
|
|
|
||
|
|
chapters = getSegments()
|
||
|
|
|
||
|
|
pdf = FPDF(unit = "pt", format = [1100, 1491])
|
||
|
|
|
||
|
|
for x in range(0, len(chapters)):
|
||
|
|
s = getPages(chapters[x][0], chapters[x][1], chapters[x][2], chapters[x][3], chapters[x][4])
|
||
|
|
outdir = chapters[x][5] + "_" + chapters[x][6]
|
||
|
|
ripPages(s, outdir, pdf)
|
||
|
|
|
||
|
|
pdf.output("ebook.pdf", "F")
|