forked from luozhaohui/python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathexportDoulistAsMarkdown.py
More file actions
executable file
·208 lines (180 loc) · 6.82 KB
/
exportDoulistAsMarkdown.py
File metadata and controls
executable file
·208 lines (180 loc) · 6.82 KB
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
#!/usr/bin/env python
#! encoding=utf-8
# Author : [email protected]
# Blog : http://kesalin.github.io
# Date : 2016/07/12
# Description : 将豆列导出为 Markdown 文件.
# Version : 1.0.0.0
# Python Version: Python 2.7.3
#
import os
import threading
import time
import datetime
import re
import string
import urllib2
from bs4 import BeautifulSoup
gHeader = {"User-Agent": "Mozilla-Firefox5.0"}
# 书籍信息类
class BookInfo:
name = ''
url = ''
icon = ''
ratingNums = ''
ratingPeople = ''
comment = ''
def __init__(self, name, url, icon, nums, people, comment):
self.name = name
self.url = url
self.icon = icon
self.ratingNums = nums
self.ratingPeople = people
self.comment = comment
# 获取 url 内容
def getHtml(url):
try :
request = urllib2.Request(url, None, gHeader)
response = urllib2.urlopen(request)
data = response.read().decode('utf-8')
except urllib2.URLError, e :
if hasattr(e, "code"):
print "The server couldn't fulfill the request: " + url
print "Error code: %s" % e.code
elif hasattr(e, "reason"):
print "We failed to reach a server. Please check your url: " + url + ", and read the Reason."
print "Reason: %s" % e.reason
return data
# 转换 html 转义字符
def decodeHtmlSpecialCharacter(htmlStr):
specChars = {" " : "", \
" " : "", \
" " : "", \
"<" : "<", \
">" : ">", \
"&" : "&", \
""" : "\"", \
"©" : "®", \
"×" : "×", \
"÷" : "÷", \
}
for key in specChars.keys():
htmlStr = htmlStr.replace(key, specChars[key])
return htmlStr
# 导出为 Markdown 格式文件
def exportToMarkdown(doulistTile, doulistAbout, bookInfos):
path = "{0}.md".format(doulistTile)
if(os.path.isfile(path)):
os.remove(path)
today = datetime.datetime.now()
todayStr = today.strftime('%Y-%m-%d %H:%M:%S %z')
file = open(path, 'a')
file.write('## {0}\n'.format(doulistTile))
file.write('{0}\n'.format(doulistAbout))
file.write('## 图书列表\n')
file.write('### 总计 {0} 本，更新时间：{1}\n'.format(len(bookInfos), todayStr))
i = 0
for book in bookInfos:
file.write('\n### No.{0:d} {1}\n'.format(i + 1, book.name))
file.write(' > **图书名称**：[{0}]({1}) \n'.format(book.name, book.url))
file.write(' > **豆瓣链接**：[{0}]({1}) \n'.format(book.url, book.url))
file.write(' > **豆瓣评分**：{0} \n'.format(book.ratingNums))
file.write(' > **评分人数**：{0} \n'.format(book.ratingPeople))
file.write(' > **我的评论**：{0} \n'.format(book.comment))
i = i + 1
file.close()
# 解析图书信息
def parseItemInfo(page, bookInfos):
soup = BeautifulSoup(page, 'html.parser')
items = soup.find_all("div", "doulist-item")
for item in items:
#itemStr = item.prettify().encode('utf-8')
#print itemStr
# get book name
content = item.find("div", "title").contents[1]
bookName = content.string.strip().encode('utf-8')
# get book url and icon
contents = item.find("div", "post")
hrefStr = contents.find('a').prettify().encode('utf-8')
#print hrefStr
bookUrl = ''
pattern = re.compile(r'(<a href=\")(.*)(\" target=)')
match = pattern.search(hrefStr)
if match:
bookUrl = match.group(2)
bookIcon = ''
pattern = re.compile(r'(img src=\")(.*)(\" width=)')
match = pattern.search(hrefStr)
if match:
bookIcon = match.group(2)
#print " > Book {0} : {1}, {2}".format(bookName, bookUrl, bookIcon)
# get rating
ratingNums = ''
ratingPeople = ''
contents = item.find("div", "rating")
for content in contents:
if content.name != None and content.string != None:
if content.get("class") != None:
ratingNums = content.string.encode('utf-8')
else:
ratingPeople = content.string.encode('utf-8')
pattern = re.compile(r'(\()(.*)(\))')
match = pattern.search(ratingPeople)
if match:
ratingPeople = match.group(2)
#print " RatingNums: {0}, ratingPeople: {1}".format(ratingNums, ratingPeople)
# get comment
comment = ''
contents = item.find_all("blockquote", "comment")
comment = contents[0].contents[2].encode('utf-8')
#print " Comment: {0}".format(comment)
# add book info to list
bookInfo = BookInfo(bookName, bookUrl, bookIcon, ratingNums, ratingPeople, comment)
bookInfos.append(bookInfo)
# 解析豆列 url
def parse(url):
start = datetime.datetime.now()
page = getHtml(url)
soup = BeautifulSoup(page, 'html.parser')
# get doulist title
doulistTile = soup.html.head.title.string.encode('utf-8')
print " > 获取豆列：" + doulistTile
# get doulist about
content = soup.find("div", "doulist-about")
#print content.prettify().encode('utf-8')
doulistAbout = ''
for child in content.children:
if child.string != None:
htmlContent = child.string.strip().encode('utf-8')
doulistAbout = "{0}\n{1}".format(doulistAbout, htmlContent)
#print "doulist about:" + doulistAbout
# get page urls
pageUrls = []
content = soup.find("div", "paginator")
for child in content.children:
childStr = "{0}".format(child)
if childStr.startswith('<a href=') == True:
childStr = decodeHtmlSpecialCharacter(childStr)
pattern = re.compile(r'(<a href=")(.*)(=">)(\d*)(</a>)')
match = pattern.search(childStr)
if match:
hrefStr = match.group(2)
pageUrls.append(hrefStr)
bookInfos = []
# get books from current page
#print " scan page : {0}".format(url)
parseItemInfo(page, bookInfos)
# get books from follow pages
for pageUrl in pageUrls:
#print " scan page : {0}".format(hrefStr)
page = getHtml(pageUrl)
parseItemInfo(page, bookInfos)
exportToMarkdown(doulistTile, doulistAbout, bookInfos)
total = len(bookInfos)
end = datetime.datetime.now()
cost = end - start
print " > 共获取 {0} 本图书信息，耗时 {1} 秒 {2} 毫秒".format(total,
cost.microseconds/1000000, (cost.microseconds%1000000)/1000)
#=============================================================================
# 程序入口：解析指定豆列
parse("https://www.douban.com/doulist/1133232/")