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
| import requests
from PIL import Image
import os
from requests.exceptions import ReadTimeout
import chardet
from bs4 import BeautifulSoup
import re
import json
import time
class GetPpt:
def __init__(self, url, savepath):
self.url = url
self.savepath = savepath if savepath != '' else os.getcwd()
self.html = ''
self.wkinfo ={}
self.ppturls = []
self.getHtml()
self.getWkInfo()
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)
return None
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 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 getImageUrlForPPT(self):
timestamp = round(time.time()*1000)
desturl = "https://wenku.baidu.com/browse/getbcsurl?doc_id="+\
self.wkinfo.get("docId")+\
"&pn=1&rn=99999&type=ppt&callback=jQuery1101000870141751143283_"+\
str(timestamp) + "&_=" + str(timestamp+1)
textdict = self.convertJsonToDict(self.getJson(desturl))
self.ppturls = [x.get('zoom') for x in textdict.get('list')]
def getImage(self, imagename, imageurl):
with open(imagename,'wb') as ig:
ig.write(requests.get(imageurl).content)
def mergeImageToPDF(self, pages):
if pages == 0:
raise IOError
namelist = [str(x)+'.png' for x in range(pages)]
firstimg = Image.open(namelist[0])
imglist = []
for imgname in namelist[1:]:
img = Image.open(imgname)
img.load()
if img.mode == 'RGBA':
img.mode = 'RGB'
imglist.append(img)
savepath = self.savepath+'/'+self.wkinfo.get('title')+'.pdf'
firstimg.save(savepath, "PDF", resolution=100.0,
save_all=True, append_images=imglist)
def removeImage(self, pages):
namelist = [str(x) + '.png' for x in range(pages)]
for name in namelist:
if os.path.exists(name):
os.remove(name)
def getPPT(self):
self.getImageUrlForPPT()
for page, url in enumerate(self.ppturls):
self.getImage(str(page)+'.png', url)
self.mergeImageToPDF(len(self.ppturls))
self.removeImage(len(self.ppturls))
if __name__ == '__main__':
GetPpt('https://wenku.baidu.com/view/6e6b9f397cd184254b3535b6.html?from=search', '存储路径').getPPT()
|
