基于百度翻译的python爬虫示例

(本年java工作真难找啊，有广州java高级岗位招人的好心人麻烦推一下，拜谢。。）
花了一周时间，从零基础开始学习了python，学有所获之后，就总想爬些什么，否则感觉不得劲，以是花了一天时间整出了个百度翻译的爬虫示例，主要卡点花在了找token、sign以及调试请求上。代码有点乱，究竟是demo，但是功能是实现了的。

1. import requests
2. import js2py
3. import re
4. from urllib.parse import urlencode
6. url = "https://fanyi.baidu.com/#zh/en/"
7. session  = requests.session()
8. headers = {
9.     'Content-Type': 'application/x-www-form-urlencoded',
10.     'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1',
11. }
13. cookies = {
14.     'BAIDUID': '624820D8D9163F370A491E7CA70C23D4:SL=0:NR=10:FG=1',
15. }
17. response = session.get(url,headers=headers,cookies=cookies)
19. print(dict(response.cookies))
21. with open('baidu.html', 'w') as f:
22.     f.write(response.content.decode())
24. token_pattern = r"token:\s*'([a-f0-9]+)'"
25. token = re.search(token_pattern, response.content.decode()).group(1)
27. gtk_pattern = "gtk:\s*'([^']+)'"
28. gtk = re.search(gtk_pattern, response.content.decode()).group(1)
30. print(token)
31. print(gtk)
35. # 获取sign
36. context = js2py.EvalJs()
37. public_js = ""
38. with open('public.js', 'r') as f:
39.     public_js += f.read()
40. context.execute(public_js)
41. context.wd = '好好学习，天天向上'
42. context.token = token
43. context.gtk = gtk
45. sug_response = session.post("https://fanyi.baidu.com/sug", data={'kw': context.wd}, headers=headers)
46. print(sug_response.json())
48. context.execute("""
49.      function n(r, o) {
50.         for (var t = 0; t < o.length - 2; t += 3) {
51.             var e = o.charAt(t + 2);
52.             e = e >= "a" ? e.charCodeAt(0) - 87 : Number(e),
53.             e = "+" === o.charAt(t + 1) ? r >>> e : r << e,
54.             r = "+" === o.charAt(t) ? r + e & 4294967295 : r ^ e
55.         }
56.         return r
57.     }
59.      function a(r) {
60.    
61.         var a = r.length;
62.         a > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(a / 2) - 5, 10) + r.substr(-10, 10))
63.       
64.         var l = void 0
65.           , d = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107);
66.         l = gtk;
67.         for (var m = l.split("."), S = Number(m[0]) || 0, s = Number(m[1]) || 0, c = [], v = 0, F = 0; F < r.length; F++) {
68.             var p = r.charCodeAt(F);
69.             128 > p ? c[v++] = p : (2048 > p ? c[v++] = p >> 6 | 192 : (55296 === (64512 & p) && F + 1 < r.length && 56320 === (64512 & r.charCodeAt(F + 1)) ? (p = 65536 + ((1023 & p) << 10) + (1023 & r.charCodeAt(++F)),
70.             c[v++] = p >> 18 | 240,
71.             c[v++] = p >> 12 & 63 | 128) : c[v++] = p >> 12 | 224,
72.             c[v++] = p >> 6 & 63 | 128),
73.             c[v++] = 63 & p | 128)
74.         }
75.         for (var w = S, A = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(97) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(54)), b = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(51) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(98)) + ("" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(102)), D = 0; D < c.length; D++)
76.             w += c[D],
77.             w = n(w, A);
78.         return w = n(w, b),
79.         w ^= s,
80.         0 > w && (w = (2147483647 & w) + 2147483648),
81.         w %= 1e6,
82.         w.toString() + "." + (w ^ S)
83.     }
85.     var sign = a(wd)
86. """)
88. print(context.sign)
91. url = 'https://fanyi.baidu.com/basetrans'
92. data = {
93.    "query": context.wd,
94.    "from": "zh",
95.    "to": "en",
96.    "token": token,
97.    "sign": context.sign
98. }
99. encoded_data = urlencode(data)
100. print(cookies)
101. print(encoded_data)
102. headers = {
103.     'Content-Type': 'application/x-www-form-urlencoded',
104.     'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1',
105. }
106. # session请求会更改user-agent {'User-Agent': 'python-requests/2.32.3', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive'}
107. print(session.headers)
108. response = requests.post(url, headers = headers,cookies=cookies,data=data, verify=True)
109. print(response.json())
112. """
113. wd=全家的执行结果：
114. {}
115. 3d7980a56760ca30e97aeeeda8e8fc6d
116. 320305.131321201
117. {'errno': 0, 'data': [{'k': '全家福', 'v': '（全家合影） a photograph of the whole family; （中餐菜名） ho'}, {'k': '全家团聚', 'v': '动. whole family gather'}], 'logid': 2318810217}
118. 681757.951340
119. {'BAIDUID': '624820D8D9163F370A491E7CA70C23D4:SL=0:NR=10:FG=1'}
120. query=%E5%85%A8%E5%AE%B6&from=zh&to=en&token=3d7980a56760ca30e97aeeeda8e8fc6d&sign=681757.951340
121. {'User-Agent': 'python-requests/2.32.3', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive'}
122. {'errno': 0, 'from': 'zh', 'to': 'en', 'trans': [{'dst': 'whole family', 'prefixWrap': 0, 'result': [[0, 'whole family', ['0|6'], [], ['0|6'], ['0|12']]], 'src': '全家'}], 'dict': {'symbols': [{'word_symbol': 'quán jiā', 'parts': [{'part_name': '名', 'means': [{'text': 'the whole family', 'word_mean': 'the whole family'}]}]}], 'word_name': '全家', 'from': 'green', 'word_means': ['the whole family']}, 'keywords': []}
125. """

复制代码

最新版本python3.13不支持js2py模块，以是我切换到了3.8版本

免责声明：如果侵犯了您的权益，请联系站长，我们会及时删除侵权内容，谢谢合作！更多信息从访问主页：qidao123.com:ToB企服之家，中国第一个企服评测及商务社交产业平台。