Cambridge dictionary 单词查询程序

信息技术 - Python - 爬虫
编程
Publish Date:   2023-10-29
Update Date:   2024-06-08
Word Count:   1.2k
Read Times:   7 Min
Read Count:  

程序会自动从 word.in 中获取信息并输出结果，输入格式如下：

第一行 $ n $ 为书本数量，以下有 $ n $ 组数据，每组的第一行为书本名称，第二行为页数 $ m $ ，下有 $ m $ 组数据，每组的第 $ 1~3 $ 行 分别为页码、标题和单词数量 $ k $ ，下有 $ k $ 个单词。

程序会自动输出 test.tex 。

请确保你安装了 requests、bs4、lxml模块。

请将以下两个文件放到同一个目录下运行。

main.py:

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
#! /usr/bin/python3
# encoding=utf-8

import requests, os, sys
from bs4 import BeautifulSoup
from write import *
# from tqdm import tqdm
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry

os.chdir(os.getcwd() + "/Something else/20231019/")



head = """
\\documentclass[a4paper,margin=1.0cm,10.5pt]{book}

\\usepackage[UTF8]{ctex}
\\usepackage{tipa}
\\usepackage{color}
\\usepackage{geometry}
\\usepackage{fontspec}
\\usepackage{xcolor}
\\usepackage{titlesec}
\\defaultfontfeatures{Ligatures=TeX}

\\setmainfont{Times New Roman}

\\renewcommand{\\large}{\\fontsize{14pt}{\\baselineskip}\\selectfont}

\\definecolor{Purple}{rgb}{.256,.0,.511}

\\newfontfamily\\sectionfont[Color=Purple]{Times New Roman}

\\titleformat*{\\section}{\\large\\bfseries\\sffamily\\color{Purple}}

\\begin{document}

\\title{Vocabulary}
\\maketitle

\\pagenumbering{roman}
\\tableofcontents
\\newpage
\\pagenumbering{arabic}
"""

tail = """\\end{document}"""

header = {
	"Cookie": 'XSRF-TOKEN=091b0a7e-7b7c-440f-82ba-7853a686d0e8; preferredDictionaries="english-chinese-simplified,english-chinese-traditional,english,british-grammar"; _ga=GA1.3.1985437458.1697684466; _gid=GA1.3.1397756659.1697684466; amp-access=amp-DgWec-PNndO292HPfqJugg; _hjFirstSeen=1; _hjSession_2790984=eyJpZCI6Ijc4ZmUwMGE3LTM0MjQtNGNhNi1hMjYwLTE3Yjc3YmQxMTE0MSIsImNyZWF0ZWQiOjE2OTc2ODQ0Njc0NTcsImluU2FtcGxlIjpmYWxzZSwic2Vzc2lvbml6ZXJCZXRhRW5hYmxlZCI6dHJ1ZX0=; _sp_ses.7ecc=*; OptanonConsent=isGpcEnabled=0&datestamp=Thu+Oct+19+2023+11%3A01%3A20+GMT%2B0800+(China+Standard+Time)&version=202308.1.0&browserGpcFlag=0&isIABGlobal=false&hosts=&landingPath=NotLandingPage&groups=C0001%3A1%2CC0002%3A1%2CC0003%3A1%2CC0004%3A0&AwaitingReconsent=false; _sp_id.7ecc=3979def0-c2d7-4674-82ae-82dabd30e180.1697684468.1.1697684480..0b270403-3325-4540-80fe-b9939b45295d....0; _hjSessionUser_2790984=eyJpZCI6IjllMjU2Zjk3LTU5ZjAtNWNhYi1hYzI4LWUyZDlhYmIzOGY4ZiIsImNyZWF0ZWQiOjE2OTc2ODQ0Njc0NTcsImV4aXN0aW5nIjp0cnVlfQ==; _gat=1; iawsc1m=1; _sharedID=54582c27-481b-45f6-af8b-567598974fc2; _sharedID_cst=zix7LPQsHA%3D%3D; _pbjs_userid_consent_data=3524755945110770; _sharedid=0362b518-b56a-4a08-9f01-687b29d9e710; _lr_retry_request=true; _lr_env_src_ats=false; pbjs-unifiedid=%7B%22TDID%22%3A%22b82f813d-b87d-406b-920c-4d28ffdd6e63%22%2C%22TDID_LOOKUP%22%3A%22TRUE%22%2C%22TDID_CREATED_AT%22%3A%222023-09-19T03%3A10%3A42%22%7D; pbjs-unifiedid_cst=zix7LPQsHA%3D%3D; loginPopup=5; _ga_L9GCR21SZ7=GS1.3.1697684466.1.1.1697685069.27.0.0; iawpvccs=4; iawpvc=4; iawpvtc1m=4; cto_bundle=-fkA8F9VeGgzOEh2TlVBQyUyQnowREg4QkhxZlY5USUyQnRrdSUyQmQ3ZHFlSTRJJTJCTmppNmt1WCUyRlFxQWhKSlNKN1d6T0NwU3Z1RUx6WmUxSmxqOWd4RHROekZuclFJZCUyRjZQYnNyTjVoSmRpUzBpSyUyQmdGWnI3bHFVZFZ4Q3YzU1hxd0JQZmMlMkJFV0NUZjAlMkZuQm96NU9BNU14M2RVSkxaS0ElM0QlM0Q; cto_bidid=PEgR8V9vZWpoUjBET21nT0lHSUhkZUMySG1WZUhYMDJFbGxmUUR5cFJxUTZhejNRY3lmNWFDZlJrRjlJTDRoMnNxQTFlaTJKd3U3Z3BWdmx0S3FBNXZVZU8xMEZmbUQwVUZKRXpRdFNqSFZYZ3RQdyUzRA',
	"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 Edg/118.0.2088.46",
	"sec-ch-ua-mobile": "0",
}

file = open("test.tex", "w+")

stdin = open("word.in", "r")

file.write(head)

# book = input("请输入书本:")

cntbook = int(stdin.readline())

lock=threading.Lock()

def solve(word):
	# templine.set_description("Processing "+nowpage)
	word = word.replace(" ","-")
	word = word.replace("/","-")
	session = requests.Session()
	retry = Retry(total=114514, backoff_factor=5)
	adapter = HTTPAdapter(max_retries=retry)
	session.mount('http://', adapter)
	session.mount('https://', adapter)
	response = session.get(
		"https://dictionary.cambridge.org/dictionary/english-chinese-simplified/"
		+ word,
		headers=header,
	)
	contentori = BeautifulSoup(response.text, "lxml")
	try:
		word = contentori.find_all("span",class_="hw dhw")[0].text
	except:
		print("Error occured on word "+word+", please check the code or spelling.")
	# tempfile = open("test.out","r")
	# temptext = tempfile.read()
	# tempfile.close()
	# content = BeautifulSoup(temptext ,"lxml")
	# print(content)
	try:
		lock.acquire()
		for content1 in contentori.find_all("div", class_="pr entry-body__el"):
			temp = content1.find_all("div", class_="pr dsense")
			pronoun=""
			try:
				pronoun = content1.find_all("span", class_="pron dpron")[0].text
			except:
				pass
			try:
				part_of_speech = content1.find_all("span", class_="pos dsense_pos")[0].text
			except:
				part_of_speech = content1.find_all("span",class_="pos dpos")[0].text
			attri=""
			try:
				attri = content1.find_all("span", class_="dgram")[0].text
			except:
				pass
			temp2 = content1.find_all("div",class_="def-block ddef_block")
			for content in temp2:
				chinese = content.find_all(
					"span", class_="trans dtrans dtrans-se break-cj"
				)[0].text
				try:
					attri = content.find_all("span", class_="dgram")[0].text
				except:
					pass
				describe = content.find_all("span", class_="guideword dsense_gw")
				example_ENG = content.find_all("span", class_="eg deg")
				example_CHI = content.find_all(
					"span", class_="trans dtrans dtrans-se hdb break-cj"
				)
				sentence = content.find_all("li", class_="eg dexamp hax")
				write(
					file,
					word,
					pronoun,
					chinese,
					part_of_speech,
					attri,
					example_CHI,
					example_ENG,
					sentence,
				)
		lock.release()
			# else:
			# 	# content = temp[0]
			# 	chinese = contentori.find_all(
			# 		"span", class_="trans dtrans dtrans-se break-cj"
			# 	)[0].text
			# 	part_of_speech = ""
			# 	try:
			# 		part_of_speech = contentori.find_all("span", class_="pos dpos")[0].text
			# 	except IndexError:
			# 		part_of_speech = contentori.find_all("span", class_="pos dsense_pos")[
			# 			0
			# 		].text
			# 	attri = ""
			# 	try:
			# 		attri = contentori.find_all("span", class_="dgram")[0].text
			# 	except:
			# 		pass
			# 	describe = contentori.find_all("span", class_="guideword dsense_gw")
			# 	example_ENG = contentori.find_all("span", class_="eg deg")
			# 	example_CHI = contentori.find_all(
			# 		"span", class_="trans dtrans dtrans-se hdb break-cj"
			# 	)
			# 	sentence = contentori.find_all("li", class_="eg dexamp hax")
			# 	write(
			# 		file,
			# 		word,
			# 		pronoun,
			# 		chinese,
			# 		part_of_speech,
			# 		attri,
			# 		example_CHI,
			# 		example_ENG,
			# 		sentence,
			# 	)
	except:
		print("Error occured on word "+word+", please check the code or spelling.")
		lock.release()
	# file.write("\n\n\n")


for nowbook in range(cntbook):
	book = stdin.readline().replace("\n","")

	page = int(stdin.readline())

	file.write("\\chapter{" + book + "}\n")

	for i in range(page):
		# temp = stdin.readline().split()
		nowpage = stdin.readline().replace("\n", "")
		# print("processing "+nowpage)
		file.write(
			"\\textcolor[RGB]{128,0,255}{\\section{"
			+ book
			+ " "
			+ nowpage
			+ " "
			+ stdin.readline().replace("\n", "")
			+ "}}\n"
		)
		# file.write("\\begin{enumerate}\n")
		# cnt = int(stdin.readline())
		cnt=int(stdin.readline())
		words=[]
		for i in range(cnt):
			words.append(stdin.readline().replace("\n",""))
		# words = stdin.readline()
		threadings = []
		for word in words:
			threadings.append(
				threading.Thread(
					target=solve,
					args=[
						word,
					],
				)
			)
		for t in threadings:
			t.start()
		# for t in threadings:
			t.join()
			


file.write(tail)
file.close()

write.py:

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
#! /usr/bin/python3
# encoding=utf-8
import threading

shape = ""

lock=threading.Lock()

def write(
	file, # 要写入的文件
	word="", # 原文
	pronunciation="", # 音标
	chinese="", # 中文
	part_of_speech="", # 词性
	attri="", # 其他属性，如是否可数
	example_CHN=[], # 例子中文
	example_ENG=[], # 例子英文
	sentence=[], # 只有英文的例句
):
	try:
		# pronunciation=pronunciation.replace("ː"," \\textlengthmark ")
		# pronunciation=pronunciation.replace("ˈ"," \\textprimstress ")
		# pronunciation=pronunciation.replace("ɪ"," \\i ")
		# pronunciation=pronunciation.replace("ɔ"," \\textopeno ")
		# pronunciation=pronunciation.replace("ɒ"," \\textturnscripta ")
		# pronunciation=pronunciation.replace("ʃ"," \\textesh ")
		# pronunciation=pronunciation.replace("ˌ", "\\textsecstress ")
		# pronunciation=pronunciation.replace("ʒ"," \\textyogh ")
		# pronunciation=pronunciation.replace("ʌ"," \\textturnv ")
		# pronunciation=pronunciation.replace("ɡ"," \\textscriptg ")
		# pronunciation=pronunciation.replace("ɑ"," \\textscripta ")
		# pronunciation=pronunciation.replace("ʊ"," \\textupsilon ")
		# pronunciation=pronunciation.replace("ɜ"," \\textrevepsilon ")
		lock.acquire()
		file.write("\\begin{itemize}\n")
		attri=attri.replace("C"," $ C $ ")
		attri=attri.replace("U"," $ U $ ")
		attri=attri.replace("I"," $ I $ ")
		attri=attri.replace("T"," $ T $ ")
		file.write("\\item "+word+" "+pronunciation+" $ "+part_of_speech+" $ "+attri+" "+chinese+"\n")
		if len(example_CHN)>0:
			file.write("\\begin{itemize}\n")
			while len(example_CHN)>3:
				example_CHN.pop()
				example_ENG.pop()
			for i in range(len(example_CHN)):
				file.write("\\item[$\\diamond$] ")
				file.write(example_ENG[i].text.replace("$"," \\$ "))
				file.write("\n")
				file.write(example_CHN[i].text.replace("%"," $ \\% $ "))
				file.write("\n")
			file.write("\\end{itemize}\n")
		# if len(sentence)!=0:
		# 	file.write("sentence:\n")
		# 	file.write("\\begin{itemize}\n")
		# 	for i in sentence:
		# 		file.write("\\item[$\\diamond$] ")
		# 		file.write(i.text)
		# 		file.write("\n")
		# 	file.write("\\end{itemize}\n")
		file.write("\\end{itemize}\n")
		lock.release()
	except:
		print("Error occured on word "+word+", please check the code or spelling.")
Author: Mozhi Hong
Link: https://greenbeanpie.github.io/2023/10/29/cambridge-dictionary-query-program/
Reprint policy: All articles in this blog are used except for special statements CC BY-NC-SA 4.0 reprint policy. If reproduced, please indicate source Mozhi Hong !
信息技术 - Python - 爬虫
赏
评论
  TOC