看有人需要下百度文库的源码,来这有一份
[*]import requests[*]import re
[*]import json
[*]import os
[*]
[*]session = requests.session()
[*]
[*]
[*]def fetch_url(url):
[*] return session.get(url).content.decode('gbk')
[*]
[*]
[*]def get_doc_id(url):
[*] return re.findall('view/(.*).html', url)
[*]
[*]
[*]def parse_type(content):
[*] return re.findall(r"docType.*?:.*?\'(.*?)\',", content)
[*]
[*]
[*]def parse_title(content):
[*] return re.findall(r"title.*?:.*?\'(.*?)\',", content)
[*]
[*]
[*]def parse_doc(content):
[*] result = ''
[*] url_list = re.findall('(https.*?0.json.*?)\\\\x22}', content)
[*] url_list =
[*] for url in url_list[:-5]:
[*] content = fetch_url(url)
[*] y = 0
[*] txtlists = re.findall('"c":"(.*?)".*?"y":(.*?),', content)
[*] for item in txtlists:
[*] if not y == item:
[*] y = item
[*] n = '\n'
[*] else:
[*] n = ''
[*] result += n
[*] result += item.encode('utf-8').decode('unicode_escape', 'ignore')
[*] return result
[*]
[*]
[*]def parse_txt(doc_id):
[*] content_url = 'https://wenku.baidu.com/api/doc/getdocinfo?callback=cb&doc_id=' + doc_id
[*] content = fetch_url(content_url)
[*] md5 = re.findall('"md5sum":"(.*?)"', content)
[*] pn = re.findall('"totalPageNum":"(.*?)"', content)
[*] rsign = re.findall('"rsign":"(.*?)"', content)
[*] content_url = 'https://wkretype.bdimg.com/retype/text/' + doc_id + '?rn=' + pn + '&type=txt' + md5 + '&rsign=' + rsign
[*] content = json.loads(fetch_url(content_url))
[*] result = ''
[*] for item in content:
[*] for i in item['parags']:
[*] result += i['c'].replace('\\r', '\r').replace('\\n', '\n')
[*] return result
[*]
[*]
[*]def parse_other(doc_id):
[*] content_url = "https://wenku.baidu.com/browse/getbcsurl?doc_id=" + doc_id + "&pn=1&rn=99999&type=ppt"
[*] content = fetch_url(content_url)
[*] url_list = re.findall('{"zoom":"(.*?)","page"', content)
[*] url_list =
[*] if not os.path.exists(doc_id):
[*] os.mkdir(doc_id)
[*] for index, url in enumerate(url_list):
[*] content = session.get(url).content
[*] path = os.path.join(doc_id, str(index) + '.jpg')
[*] with open(path, 'wb') as f:
[*] f.write(content)
[*] print("图片保存在" + doc_id + "文件夹")
[*]
[*]
[*]def save_file(filename, content):
[*] with open(filename, 'w', encoding='utf8') as f:
[*] f.write(content)
[*] print('已保存为:' + filename)
[*]
[*]
[*]def main():
[*] url = input('请输入要下载的文库URL地址_')
[*] content = fetch_url(url)
[*] doc_id = get_doc_id(url)
[*] Type = parse_type(content)
[*] title = parse_title(content)
[*] if Type == 'doc':
[*] result = parse_doc(content)
[*] save_file(title + '.txt', result)
[*] elif Type == 'txt':
[*] result = parse_txt(doc_id)
[*] save_file(title + '.txt', result)
[*] else:
[*] parse_other(doc_id)
[*]
[*]
[*]if __name__ == "__main__":
[*] main()复制代码
imgchr.404.png
imgchr.404.png
imgchr.404.png
战略性标记 mark 战略mark 战略性mark 本帖最后由 shares 于 2019-3-15 22:49 编辑
看见了
下载的是图片
如果能是源文档就完美了
还是谢谢了 不是可以直接下载原文档吗 楼主666啊，标记一下 来个教程啊标记
shy.gif
学呀，今晚技术大牛多
页:
[1]
2