08.14自己概要
爬虫類アナログ適切な方法辞書翻訳
A.コード
import requests
from lxml.html import etree
# headers= {
# 'User-Agent':' Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36',
# 'Cookie':' DICT_UGC=be3af0da19b5c5e6aa4e17bd8d90b28a|; webDict_HdAD=%7B%22req%22%3A%22http%3A//dict.youdao.com%22%2C%22width%22%3A960%2C%22height%22%3A240%2C%22showtime%22%3A5000%2C%22fadetime%22%3A500%2C%22notShowInterval%22%3A3%2C%22notShowInDays%22%3Afalse%2C%22lastShowDate%22%3A%22Mon%20Nov%2008%202010%22%7D; ___rl__test__cookies=1565782601235; [email protected]; OUTFOX_SEARCH_USER_ID_NCOO=1369535179.7407944; _ntes_nnid=b3ad33663a64ae962e76c71b2df46330,1565057224869; JSESSIONID=abcfltcZlc31Td7QD1pYw; search-popup-show=8-14; DICT_UGC=be3af0da19b5c5e6aa4e17bd8d90b28a|; ___rl__test__cookies=1565782014056'
# }
#本来以为有道可能会有点反爬措施,结果发现并没有...
a = input('请输入你翻译的内容')
rp = requests.get(f'https://dict.youdao.com/w/{a}/') #这个url是Fiddler获得的
#他翻译的内容可能会出现在两个xpath中
data_xpath_1 = '//*[@id="phrsListTab"]/div/ul/li/text()'
html = etree.HTML(rp.text)
data = html.xpath(data_xpath_1)
if not data:
data_xpath_2 = '//*[@id="phrsListTab"]/div/ul/p/span[2]/a/text()'
data = html.xpath(data_xpath_2)
#单纯的为了打印好看
count = 1
for english in data:
print(f'翻译{count}:{english}')
count += 1
私はまた、楽しいJSた
https://dict.youdao.com/word/wordarticle?query= 这里是我们查询的翻译输入的内容＆JSONP = _ = 1,565,783,847,668 jQuery191018231021198201125_1565783847667＆HTTP / 1.1
あなたは天才を入力しようとすることができるコンテンツの多くが一致しませんが、
関連記事に一致しています