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
|
from urllib.request import urlopen, urlretrieve
from urllib.parse import urlparse, urlunparse
import re
import os
from time import sleep
class MoinSpider:
def __init__(self, site='fox.vincefn.net',
exclude=["RecentChanges", "action=",
"FindPage", "TitleIndex", "WordIndex",
"Help", "template", "Template", "MoinMoin",
"UserPreferences", "WikiSandBox",
"ScriptAlias", "ScriptAlias"]):
# self.u.addheader(('USER_AGENT', 'Mozilla/4.0'))
self.base = 'href=\"/'
self.suffix = "?action=print"
self.site = site
self.pages = [] # list of pairs [relative URL, page content]
self.d = {} # dictionnary with keys=relative URL, value= short filename for the downloaded page
self.exclude = exclude
self.nbFail = 0 # pages which failed to load
self.img = set()
def Weave(self, lnk='/Fox/FoxWiki', nbtry=3):
""" Download recursively all pages, starting from one relative URL.
"""
if self.d.has_key(lnk): # we already got that page !
return
self.d[lnk] = "wiki_%i.html" % (1000 + len(self.d))
url = "http://" + self.site + lnk + self.suffix #:TODO: use urlparse !
print()
print("Getting page: %s" % url)
print(" -> %s" % (self.d[lnk]))
nb = nbtry
cont = True
while (nb > 0):
try:
p = urlopen(url)
page = p.read().decode('utf-8')
nb = -1
except IOError:
nb -= 1
print("IOError..... retry #%i" % (nbtry - nb))
sleep(1)
if nb == 0:
print("Failed to load page, after %i trials:" % nbtry, lnk)
self.nbFail += 1
return
if re.search("This page does not exist yet", page) is not None:
print(" -> Page has not been written yet !")
self.d[lnk] = "http://" + self.site + lnk # Link directly to site
return
self.pages.append([lnk, page])
for m in re.finditer(r"href\=\"(.*?)\"", page):
newlink = m.group()
if len(newlink) >= len(self.base):
if newlink[:len(self.base)] == self.base:
keep = True
for x in self.exclude:
if re.search(x, newlink) != None:
keep = False
break
if keep:
# print(" ->%s"%newlink)
newlink = newlink[6:-1] # [6:-1] -> exlude ' href=" ' and the end ' " '
newlink = re.split('#', newlink)[0] # exclude anchors
self.Weave(newlink)
# else:
# print(" ->%s ? NO"%newlink)
def WeaveStatic(self, pagelist, nbtry=3):
""" Alternative to weave: download a pre-selected list of pages
"""
for lnk in pagelist:
self.d[lnk] = "wiki_%i.html" % (1000 + len(self.d))
url = "http://" + self.site + lnk + self.suffix #:TODO: use urlparse !
print("Getting page: %s -> %s" % (url, self.d[lnk]))
nb = nbtry
cont = True
while (nb > 0):
try:
print(url)
p = urlopen(url)
page = p.read().decode('utf-8')
nb = -1
except IOError:
nb -= 1
print("IOError..... retry #%i" % (nbtry - nb))
sleep(1)
if nb == 0:
print("Failed to load page, after %i trials:" % nbtry, lnk)
if re.search("This page does not exist yet", page) is not None:
print(" -> Page has not been written yet !")
self.d[lnk] = "http://" + self.site + lnk # Link directly to site
nb = 0
else:
self.pages.append([lnk, page])
def Pages2Html(self, d="wikihtml"):
# TODO : remove links to non-written pages
if not os.path.exists(d):
os.mkdir(d)
# this is necessary so that urls that contain other (smaller) urls
# are replaced first
ks = list(self.d.keys())
ks.sort(reverse=True)
for p in self.pages:
for m in re.finditer(r"img .*? src\=\"(.*?)\"", p[1]):
print(re.findall(r"src\=\"(.*?)\"", m.group()))
url = re.findall(r"src\=\"(.*?)\"", m.group())[0]
up = urlparse(url)
print(url)
up0, up1, up2, up3, up4, up5 = up[0], up[1], up[2], up[3], up[4], up[5]
if up4 != '':
name = re.split('=', up4).pop()
else:
name = re.split('/', up2).pop()
if name not in self.img: # download image once
self.img.add(name)
if up0 == '':
up0 = 'http'
if up1 == '':
up1 = self.site
urlimg = urlunparse((up0, up1, up2, up3, up4, up5)).replace('&', '&')
print(" %s -> %s" % (urlimg, name))
nbTry = 3
nb = nbTry
while nb > 0:
try:
urlretrieve(urlimg, d + "/" + name)
nb = -1
except IOError:
nb -= 1
print("IOError..... retry #%i to get %s" % (nbTry - nb, name))
sleep(1)
if nb == 0:
print("Failed to load image, after %i trials: %s" % (nbtry, name))
else: # KLUDGE png->png cause htmldoc chokes on these...
if name[-4:] == ".png":
print("convert %s %s" % (d + "/" + name, d + "/" + name[:-3] + "jpg"))
os.system("convert %s %s" % (d + "/" + name, d + "/" + name[:-3] + "jpg"))
os.system("rm -f %s" % (d + "/" + name))
p[1] = p[1].replace(url, name)
for k in ks: # change to local url
if k != self.d[k]:
p[1] = p[1].replace(k, self.d[k])
# Change src field of img from "wiki_1002.html?action=AttachFile&do=get&target=toto.jpg"
# to "toto.jpg"
p[1] = p[1].replace("%s?action=AttachFile&do=get&target=" % k, "")
p[1] = p[1].replace(".png", ".jpg")
f = open(d + "/" + self.d[p[0]], 'w')
f.write(p[1])
def Html2pdf(self, d="wikihtml"):
os.system("mogrify -resize '600x>' wikihtml/*.jpg")
# os.system("htmldoc --jpeg=85 --webpage %s/*.html --linkcolor blue -f wiki.pdf"%d)
os.system("htmldoc --jpeg=85 --webpage %s/*.html --linkcolor blue --size a4 --format pdf14 "
"--links --book --toclevels 3 --left 1.5cm --right 1.5cm --top 1.5cm --bottom 1.5cm "
"--footer Dc1 -f FoxManual.pdf" % d)
# os.system("rm -f wikihtml/*")
# m=MoinSpider(site="objcryst.sourceforge.net")
m = MoinSpider(site="fox.vincefn.net")
m.WeaveStatic(["/FoxWiki",
"/BiblioReferences",
"/Screenshots",
"/Download",
"/Install",
"/Install/Linux",
"/Install/MacOSX",
"/Install/Windows",
"/Tutorials",
"/Tutorials/Cimetidine",
"/Tutorials/PbSO4",
"/Tutorials/YLID",
"/Manual",
"/Manual/Crystal",
"/Manual/Powder",
"/Manual/Indexing",
"/Manual/ProfileFitting",
"/Manual/SingleCrystalDiffraction",
"/Manual/Algorithm",
"/Manual/CIF",
"/Manual/Fox.Grid",
"/Manual/Tips",
"/MailingList",
"/Changelog",
"/FoxCompile",
"/Compile/Linux",
"/Compile/MacOSX",
# "/Compile/Windows"
# "/BiblioStructures",
# "/VincentFavreNicolin"
])
m.Pages2Html()
m.Html2pdf()
|
