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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
| import requests
import os
from requests.exceptions import ReadTimeout
import chardet
from bs4 import BeautifulSoup
import re
import json
import math
from PIL import Image
import pdfkit
from GetPpt import GetPpt
import time
class GetAll:
def __init__(self, url, savepath):
"""
:param url: 待爬取文档所在页面的url
:param savepath: 生成文档保存路径
"""
self.url = url
self.savepath = savepath if savepath != '' else os.getcwd()
self.startpage = 1
self.url = self.url + "&pn=1"
self.html = ''
self.wkinfo ={}
self.jsonurls = []
self.pdfurls = []
self.getHtml()
self.getWkInfo()
self.htmlsdirpath = self.makeDirForHtmlSave()
self.pdfsdirpath = self.makeDirForPdfSave()
self.htmlfile = self.wkinfo.get('title')+".html"
def makeDirForHtmlSave(self):
if not os.path.exists(os.path.join(self.savepath,'htmlfiles')):
os.mkdir(os.path.join(self.savepath,'htmlfiles'))
return os.path.join(self.savepath, 'htmlfiles')
def makeDirForPdfSave(self):
if not os.path.exists(os.path.join(self.savepath, 'pdffiles')):
os.mkdir(os.path.join(self.savepath,'pdffiles'))
return os.path.join(self.savepath,'pdffiles')
def creatHtml(self):
with open(os.path.join(self.htmlsdirpath, str(self.startpage) + self.htmlfile), "w") as f:
message = """
<!DOCTYPE html>
<html class="expanded screen-max">
<head>
<meta charset="utf-8">
<title>文库</title>"""
f.write(message)
def addMessageToHtml(self,message):
""":param message:向html文档中添加内容 """
with open(os.path.join(self.htmlsdirpath, str(self.startpage) + self.htmlfile), "a", encoding='utf-8') as a:
a.write(message)
def getHtml(self):
try:
header = {'User-Agent': 'Mozilla/5.0 '
'(Macintosh; Intel Mac OS X 10_14_6) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/78.0.3904.108 Safari/537.36'}
response = requests.get(self.url, headers = header)
self.transfromEncoding(response)
self.html = BeautifulSoup(response.text, 'html.parser')
except ReadTimeout as e:
print(e)
def transfromEncoding(self, html):
html.encoding = chardet.detect(html.content).get("encoding")
def getWkInfo(self):
items = ["'title'","'docType'","'docId'","'totalPageNum"]
for item in items:
ls = re.findall(item+".*'", str(self.html))
if len(ls) != 0:
message = ls[0].split(':')
self.wkinfo[eval(message[0])] = eval(message[1])
def getJsonUrl(self):
urlinfo = re.findall("WkInfo.htmlUrls = '.*?;", str(self.html))
urls = re.findall("https:.*?}", urlinfo[0])
urls = [str(url).replace("\\", "").replace('x22}','') for url in urls ]
self.jsonurls = urls
def getJson(self, url):
"""
:param url: json文件所在页面的url
:return: json格式字符串
"""
response = requests.get(url)
jsonstr = response.text[response.text.find('(')+1: response.text.rfind(')')]
return jsonstr
def convertJsonToDict(self, jsonstr):
"""
:param jsonstr: json格式字符串
:return: json字符串所对应的python字典
"""
textdict = json.loads(jsonstr)
return textdict
def isPptStyle(self):
iswholepic = False
ispptlike = False
for url in self.jsonurls:
if "0.json" in url:
textdict = self.convertJsonToDict(self.getJson(url))
if textdict.get("style") == "" and textdict.get("font") is None:
iswholepic = True
break
elif textdict.get('page').get('pptlike'):
ispptlike = True
break
break
return iswholepic and ispptlike
def getCssUrl(self):
pattern = re.compile('<link href="//.*?\.css')
allmessage = pattern.findall(str(self.html))
allcss = [x.replace('<link href="', "https:") for x in allmessage]
return allcss
def getPageTag(self):
""":return:返回id属性包含 data-page-no 的所有标签,即所有页面的首标签"""
def attributeFilter(tag):
return tag.has_attr('data-page-no')
return self.html.find_all(attributeFilter)
def getDocIdUpdate(self):
""":return:doc_id_update字符串"""
pattern = re.compile('doc_id_update:".*?"')
for i in pattern.findall(str(self.html)):
return i.split('"')[1]
def getAllReaderRenderStyle(self):
""":return: style <id = "reader - render - style">全部内容"""
page = 1
style = '<style id='+'"reader-render-style">\n'
for url in self.jsonurls:
if "json" in url:
textdict = self.convertJsonToDict(self.getJson(url))
style += self.getReaderRenderStyle(textdict.get('style'), textdict.get('font'), textdict.get('font'), page)
page += 1
else:
break
style += "</style>\n"
return style
def getReaderRenderStyle(self, allstyle, font, r, page):
"""
:param allstyle: json数据的style内容
:param font: json数据的font内容
:param r: TODO:解析作用未知,先取值与e相同
:param page: 当前页面
:return: style <id = "reader - render - style">
"""
p, stylecontent = "", []
for index in range(len(allstyle)):
style = allstyle[index]
if style.get('s'):
p = self.getPartReaderRenderStyle(style.get('s'), font, r).strip(" ")
l = "reader-word-s" + str(page) + "-"
p and stylecontent.append("." + l + (",." + l).join([str(x) for x in style.get('c')]) + "{ " + p + "}")
if style.get('s').get("font-family"):
pass
stylecontent.append("#pageNo-" + str(page) + " .reader-parent{visibility:visible;}")
return "".join(stylecontent)
def getPartReaderRenderStyle(self, s, font, r):
"""
:param s: json style下的s属性
:param font: json font属性
:param r: fontMapping TODO:先取为与e相同
:return: style <id = "reader - render - style">中的部分字符串
"""
content = []
n, p = 10, 1349.19 / 1262.85
def fontsize(f):
content.append("font-size:" + str(math.floor(eval(f) * n * p)) + "px;")
def letterspacing(l):
content.append("letter-spacing:" + str(eval(l) * n) + "px;")
def bold(b):
"false" == b or content.append("font-weight:600;")
def fontfamily(o):
n = font.get(o) or o if font else o
content.append("font-family:'" + n + "','" + o + "','" + (r.get(n) and r[n] or n) + "';")
for attribute in s:
if attribute == "font-size":
fontsize(s[attribute])
elif attribute == "letter-spacing":
letterspacing(s[attribute])
elif attribute == "bold":
bold(s[attribute])
elif attribute == "font-family":
fontfamily(s[attribute])
else:
content.append(attribute + ":" + s[attribute] + ";")
return "".join(content)
def AddCss(self):
urls = self.getCssUrl()
urls = [url for url in urls if "htmlReader" in url or "core" in url or "main" in url or "base" in url]
for url in urls:
message = '<style type="text/css">'+requests.get(url).text+"</style>>"
self.addMessageToHtml(message)
content = self.getAllReaderRenderStyle()
self.addMessageToHtml(content)
def addMainContent(self):
"""
:param startpage: 开始生成的页面数
:return:
"""
self.addMessageToHtml("\n\n\n<body>\n")
docidupdate = self.getDocIdUpdate()
jsonurl = [x for x in self.jsonurls if "json" in x]
pngurl = [x for x in self.jsonurls if "png" in x]
tags = self.getPageTag()
for page, tag in enumerate(tags):
if page > 50:
break
tag['style'] = "height: 1349.19px;"
tag['id'] = "pageNo-" + str(page+1)
self.addMessageToHtml(str(tag).replace('</div>', ''))
diu = self.getDocIdUpdate()
n = "-webkit-transform:scale(1.00);-webkit-transform-origin:left top;"
textdict = self.convertJsonToDict(self.getJson(jsonurl[page]))
if page < len(pngurl):
maincontent = self.creatMainContent(textdict.get('body'), textdict.get('page'), textdict.get('font'), page + 1, docidupdate,
pngurl[page])
else:
maincontent = self.creatMainContent(textdict.get('body'), textdict.get('page'), textdict.get('font'), page + 1, docidupdate, "")
content = "".join([
'<div class="reader-parent-' + diu + " reader-parent " + '" style="position:relative;top:0;left:0;' + n + '">',
'<div class="reader-wrap' + diu + '" style="position:absolute;top:0;left:0;width:100%;height:100%;">',
'<div class="reader-main-' + diu + '" style="position:relative;top:0;left:0;width:100%;height:100%;">', maincontent,
"</div>", "</div>", "</div>", "</div>"])
self.addMessageToHtml(content)
print("已完成%s页的写入,当前写入进度为%f" % (str(page+self.startpage), 100*(page+self.startpage)/int(self.wkinfo.get('totalPageNum'))) + '%')
self.addMessageToHtml("\n\n\n</body>\n</html>")
def isNumber(self, obj):
"""
:param obj:任意对象
:return: obj是否为数字
"""
return isinstance(obj, int) or isinstance(obj, float)
def creatMainContent(self, body, page, font, currentpage, o, pngurl):
"""
:param body: body属性
:param page: page属性
:param font: font属性
:param currentpage: 当前页面数
:param o:doc_id_update
:param pngurl: 图片所在url
:return:文本及图片的html内容字符串
"""
content, p, s, h = 0, 0, 0, 0
main = []
l = 2
c = page.get('v')
d = font
y = {
"pic": '<div class="reader-pic-layer" style="z-index:__NUM__"><div class="ie-fix">',
"word": '<div class="reader-txt-layer" style="z-index:__NUM__"><div class="ie-fix">'
}
g = "</div></div>"
MAX1 , MAX2 = 0, 0
body = sorted(body, key=lambda k: k.get('p').get('z'))
for index in range(len(body)):
content = body[index]
if "pic" == content.get('t'):
MAX1 = max(MAX1, content.get('c').get('ih') + content.get('c').get('iy') + 5)
MAX2 = max(MAX2, content.get('c').get('iw'))
for index in range(len(body)):
content = body[index]
s = content.get('t')
if not p:
p = h = s
if p == s:
if content.get('t') == "word":
main.append(self.creatTagOfWord(content, currentpage, font, d, c))
elif content.get('t') == 'pic':
main.append(self.creatTagOfImage(content, pngurl, MAX1, MAX2))
else:
main.append(g)
main.append(y.get(s).replace('__NUM__', str(l)))
l += 1
if content.get('t') == "word":
main.append(self.creatTagOfWord(content, currentpage, font, d, c))
elif content.get('t') == 'pic':
main.append(self.creatTagOfImage(content, pngurl, MAX1, MAX2))
p = s
return y.get(h).replace('__NUM__', "1") + "".join(main) + g
def creatTagOfWord(self, t, currentpage, font, o, version, *args):
"""
:param t: body中的每个属性
:param currentpage: page
:param font: font属性
:param o:font属性
:param version: page中的version属性
:param args:
:return:<p>标签--文本内容
"""
p = t.get('p')
ps = t.get('ps')
s = t.get('s')
z = ['<b style="font-family:simsun;"> </b>', "\n"]
k, N = 10, 1349.19 / 1262.85
U = self.O(ps)
w, h, y, x, D= p.get('w'), p.get('h'), p.get('y'), p.get('x'), p.get('z')
pattern=re.compile("[\s\t\0xa0]| [\0xa0\s\t]$")
final = []
if U and ps and ((ps.get('_opacity') and ps.get('_opacity') == 1) or (ps.get('_alpha') and ps.get('_alpha') == 0)):
return ""
else:
width = math.floor(w * k * N)
height = math.floor(h * k * N)
final.append("<p "+'class="'+"reader-word-layer" + self.processStyleOfR(t.get('r'), currentpage) + '" ' + 'style="' + "width:" +str(width) + "px;" + "height:" + str(height) + "px;" + "line-height:" + str(height) + "px;")
final.append("top:"+str(math.floor(y * k * N))+"px;"+"left:"+str(math.floor(x * k * N))+"px;"+"z-index:"+str(D)+";")
final.append(self.processStyleOfS(s, font, o, version))
final.append(self.processStyleOf_rotate(ps.get('_rotate'), w, h, x, y, k, N) if U and ps and self.isNumber(ps.get('_rotate')) else "")
final.append(self.processStyleOfOpacity(ps.get('_opacity')) if U and ps and ps.get('_opacity') else "")
final.append(self.processStyleOf_scaleX(ps.get('_scaleX'), width, height) if U and ps and ps.get('_scaleX') else "")
final.append(str(isinstance(t.get('c'), str) and len(t.get('c')) == 1 and pattern.match(t.get('c')) and "font-family:simsun;") if isinstance(t.get('c'), str) and len(t.get('c')) == 1 and pattern.match(t.get('c')) else "")
final.append('">')
final.append(t.get('c') if t.get('c') else "")
final.append(U and ps and str(self.isNumber(ps.get('_enter'))) and z[ps.get('_enter') if ps.get('_enter') else 1] or "")
final.append("</p>")
return "".join(final)
def processStyleOfS(self, t, font, r, version):
"""
:param t: 文本的s属性
:param font: font属性
:param r:font属性
:param version:
:return:处理好的S属性字符串
"""
infoOfS = []
n = {"font-size": 1}
p , u = 10, 1349.19 / 1262.85
def fontfamily(o):
n = font.get(o) or o if font else o
if abs(version) > 5:
infoOfS.append("font-family:'"+ n + "','" + o + "','" + (r.get('n') and r[n] or n) + "';")
else:
infoOfS.append("font-family:'" + o + "','" + n + "','" + (r.get(n) and r[n] or n) + "';")
def bold(e):
"false" == e or infoOfS.append("font-weight:600;")
def letter(e):
infoOfS.append("letter-spacing:" + str(eval(e) * p) + "px;")
if t is not None:
for attribute in t:
if attribute == "font-family":
fontfamily(t[attribute])
elif attribute == "bold":
bold(t[attribute])
elif attribute == "letter-spacing":
letter(t[attribute])
else:
infoOfS.append(attribute + ":" + (str(math.floor(((t[attribute] if self.isNumber(t[attribute]) else eval(t[attribute])) * p * u))) + "px" if n.get(attribute) else t[attribute]) + ";")
return "".join(infoOfS)
def processStyleOfR(self, r, page):
"""
:param r: 文本的r属性
:param page: 当前页面
:return:
"""
l = " " + "reader-word-s" + str(page) + "-"
return "".join([l + str(x) for x in r]) if isinstance(r, list) and len(r) != 0 else ""
def processStyleOf_rotate(self, t, w, h, x, y, k, N):
"""
:param t: _rotate属性
:param w: body中p.w
:param h: body中p.h
:param x: body中p.x
:param y: body中p.y
:param k: 倍数10
:param N: 比例系数
:return: 处理好的_rotate属性字符串
"""
p = []
s = k * N
if t == 90:
p.append("left:" + str(math.floor(x + (w - h) / 2) * s) + "px;" + "top:" + str(math.floor(y - (h - w) / 2) * s) + "px;" + "text-align: right;" + "height:" + str(math.floor(h + 7) * s) + "px;")
elif t == 180:
p.append("left:" + str(math.floor(x - w) * s) + "px;" + "top:" + str(math.floor(y - h) * s) + "px;")
elif t == 270:
p.append("left:" + str(math.floor(x + (h - w) / 2) * s) + "px;" + "top:" + str(math.floor(y - (w - h) / 2) * s) + "px;")
return "-webkit-"+"transform:rotate("+str(t)+"deg);"+"".join(p)
def processStyleOf_scaleX(self, t, width, height):
"""
:param t: _scaleX属性
:param width: 计算好的页面width
:param height:计算好的页面height
:return: 处理好的_scaleX属性字符串
"""
return "-webkit-" + "transform: scaleX(" + str(t) + ");" + "-webkit-" + "transform-origin:left top;width:" + str(width + math.floor(width / 2)) + "px;height:" + str(height + math.floor(height / 2)) + "px;"
def processStyleOfOpacity(self,t):
"""
:param t: opacity属性
:return:处理好的opacity属性字符串
"""
t = (t or 0),
return "opacity:" + str(t) + ";"
def creatTagOfImage(self,t,url, *args):
"""
:param t: 图片的字典
:param url:图片链接
:param args:
:return:图像标签
"""
u, l = t.get('p'), t.get('c')
if u.get("opacity") and u.get('opacity') == 0:
return ""
else:
if u.get("x1") or (u.get('rotate') != 0 and u.get('opacity') != 1):
message = '<div class="reader-pic-item" style="' + "background-image: url(" + url + ");" + "background-position:" + str(-l.get('ix')) + "px " + str(-l.get('iy')) + "px;" \
+ "width:" + str(l.get('iw')) + "px;" + "height:" + str(l.get('ih')) + "px;" + self.getStyleOfImage(u, l) + 'position:absolute;overflow:hidden;"></div>'
else:
[s, h] = [str(x) for x in args]
message = '<p class="reader-pic-item" style="' + "width:" + str(l.get('iw')) + "px;" + "height:" + str(l.get('ih')) + "px;" + self.getStyleOfImage(u, l) + 'position:absolute;overflow:hidden;"><img width="' + str(h) + '" height="' + str(s) + '" style="position:absolute;top:-' + str(l.get('iy')) + "px;left:-" + str(l.get('ix')) + "px;clip:rect(" + str(l.get('iy')) + "px," + str(int(h) - l.get('ix')) + "px, " + str(s) + "px, " + str(l.get('ix')) + 'px);" src="' + url + '" alt=""></p>'
return message
def getStyleOfImage(self, t, e):
"""
:param t: 图片p属性
:param e: 图片c属性
:return:
"""
def parseFloat(string):
"""
:param string:待处理的字符串
:return: 返回字符串中的首个有效float值，若字符首位为非数字，则返回nan
"""
if string is None:
return math.nan
elif isinstance(string, float):
return string
elif isinstance(string, int):
return float(string)
elif string[0] != ' ' and not str.isdigit(string[0]):
return math.nan
else:
p = re.compile("\d+\.?\d*")
all = p.findall(string)
return float(all[0]) if len(all) != 0 else math.nan
if t is None:
return ""
else:
r, o, a, n = 0, 0, "", 0
iw = e.get('iw')
ih = e.get('ih')
u = 1349.19 / 1262.85
l = str(t.get('x') * u) + "px"
c = str(t.get('y') * u) + "px"
d = ""
x = {}
w = {"opacity": 1, "rotate": 1, "z": 1}
for n in t:
x[n] = t[n] * u if (self.isNumber(t[n]) and not w.get(n)) else t[n]
if x.get('w') != iw or x.get('h') != ih:
if x.get('x1'):
a = self.P(x.get('x0'), x.get('y0'), x.get('x1'), x.get('y1'), x.get('x2'), x.get('y2'))
r = parseFloat(parseFloat(a[0])/iw if len(a) else x.get('w') / iw)
o = parseFloat(parseFloat(a[1])/ih if len(a) else x.get('h') / ih)
m, v = iw * (r-1), ih * (o-1)
c = str((x.get('y1') + x.get('y3')) / 2 - parseFloat(ih) / 2)+"px" if x.get('x1') else str(x.get('y') + v / 2) + "px"
l = str((x.get('x1') + x.get('x3')) / 2 - parseFloat(iw) / 2)+"px" if x.get('x1') else str(x.get('x') + m / 2) + "px"
d = "-webkit-" + "transform:scale(" + str(r) + "," + str(o) + ")"
message = "z-index:" + str(x.get('z')) + ";" + "left:" + l + ";" + "top:" + c + ";" + "opacity:" + str(x.get('opacity') or 1) + ";"
if x.get('x1'):
message += self.O(x.get('rotate')) if x.get('rotate') > 0.01 else self.O(0, x.get('x1'), x.get('x2'), x.get('y0'), x.get('y1'), d)
else:
message += d + ";"
return message
def P(self,t, e, r, i, o, a):
p = round(math.sqrt(math.pow(abs(t - r), 2) + math.pow(abs(e - i), 2)), 4)
s = round(math.sqrt(math.pow(abs(r - o), 2) + math.pow(abs(i - a), 2)), 4)
return [s, p]
def O(self, t, *args):
[e, r, i, o, a] = [0, 0, 0, 0, ""] if len(args) == 0 else [x for x in args]
n = o > i
p = e > r
if n and p:
a += " Matrix(1,0,0,-1,0,0)"
elif n:
a += " Matrix(1,0,0,-1,0,0)"
elif p:
a += " Matrix(-1,0,0,1,0,0)"
elif t:
a += " rotate(" + str(t) + "deg)"
return a + ";"
def convertHtmlToPdf(self):
savepath = os.path.join(self.pdfsdirpath, str(self.startpage)+self.wkinfo.get('title') + '.pdf')
exactpages = int(self.wkinfo.get('totalPageNum'))
if exactpages > 50:
exactpages = 50
options = {'disable-smart-shrinking':'',
'lowquality': '',
'image-quality': 60,
'page-height': str(1349.19*0.26458333),
'page-width': '291',
'margin-bottom': '0',
'margin-top': '0',
}
pdfkit.from_file(os.path.join(self.htmlsdirpath, str(self.startpage) + self.htmlfile), savepath, options=options)
def Run(self):
self.getJsonUrl()
if self.isPptStyle():
GetPpt(self.url, self.savepath).getPPT()
else:
for epoch in range(int(int(self.wkinfo.get('totalPageNum'))/50)+1):
self.startpage = epoch * 50 + 1
if epoch == 0:
self.creatHtml()
start = time.time()
print('-------------Start Add Css--------------')
self.AddCss()
print('-------------Css Add Finissed-----------')
end = time.time()
print("Add Css Cost: %ss" % str(end - start))
start = time.time()
print('-------------Start Add Content----------')
self.addMainContent()
print('-------------Content Add Finished-------')
end = time.time()
print("Add MainContent Cost: %ss" % str(end - start))
start = time.time()
print('-------------Start Convert--------------')
self.convertHtmlToPdf()
print('-------------Convert Finished-----------')
end = time.time()
print("Convert Cost: %ss" % str(end - start))
else:
self.url = self.url[:self.url.find('&pn=')] + "&pn=" + str(self.startpage)
print(self.url)
self.getHtml()
self.getJsonUrl()
self.creatHtml()
start = time.time()
print('-------------Start Add Css--------------')
self.AddCss()
print('-------------Css Add Finissed-----------')
end = time.time()
print("Add Css Cost: %ss" % str(end - start))
start = time.time()
print('-------------Start Add Content----------')
self.addMainContent()
print('-------------Content Add Finished-------')
end = time.time()
print("Add MainContent Cost: %ss" % str(end - start))
start = time.time()
print('-------------Start Convert--------------')
self.convertHtmlToPdf()
print('-------------Convert Finished-----------')
end = time.time()
print("Convert Cost: %ss" % str(end - start))
if __name__ == '__main__':
GetAll('https://wenku.baidu.com/view/fb92d7d3b8d528ea81c758f5f61fb7360a4c2b61.html?from=search',"存储路径").Run()
|
