python常用模块

# coding = utf-8
"""
1.常用模块学习记录
"""
import docx
import xlrd
from io import StringIO
from io import open
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
import re
import xlwt
import random


class Study(object):
    """常用模块学习记录"""

    def __init__(self):
        """初始化"""
        self.user_agent = [
            "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.135 Safari/537.36",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36"
        ]
        num = random.randint(0, 3)  # 生产0-3的随机数
        self.headers = {
            "User-Agent": self.user_agent[num]
        }

    def read_from_docx(self):
        """读取docx: https://zhuanlan.zhihu.com/p/38251812文件"""
        # 1.打开word文件，读取word文本
        file = docx.opendocx("./XXX.docx")
        text_list = docx.getdocumenttext(file)  # type: list
        # print(type(text_list), text_list)
        # 2.将列表中的内容按空格拼接为字符串
        text = " ".join(text_list)  # type: str
        print(type(text), text)
        return text

    def read_from_excel(self):
        """读取Excel文件：https://www.jianshu.com/p/f2c9dff344c6"""
        # 打开Excel表格
        workbook1 = xlrd.open_workbook("./XXX.xlsx")  # xlrd.book.Book object
        workbook2 = xlrd.open_workbook("./XXX.xls")
        # 获取所有sheet名称
        sheet_names1 = workbook1.sheet_names()  # type: list
        sheet_names2 = workbook2.sheet_names()  # type: list
        # print(sheet_names1, sheet_names2)
        # 获取所有sheet对象
        sheet_objects = workbook1.sheets()  # [<xlrd.sheet.Sheet object at 0x00000215E93774F0>]
        # 通过index获取第一个sheet对象
        sheet1_object = workbook1.sheet_by_index(0)  # <xlrd.sheet.Sheet object at 0x0000015D21327490>
        # 通过name获取第一个sheet对象
        sheet1_object = workbook1.sheet_by_name(sheet_name="Sheet1")  # <xlrd.sheet.Sheet object at 0x0000015D21327490>
        # 获取sheet1中第3行的数据
        row3_values = sheet1_object.row_values(rowx=2)  # type: list
        print(row3_values)
        # 获取sheet1中第3行第2列数据
        row3_column2_value = sheet1_object.row_values(2, 1, 2)  # type: list
        # row3_column2_value = sheet1_object.row_values(rowx=2, start_colx=1, end_colx=2)  # type: list
        print(row3_column2_value)

    def read_from_pdf(self):
        """读取pdf文件:https://blog.csdn.net/Artificial_idiots/article/details/108733280"""
        pdf_filename = 'F:/XX/文献资料/XX.pdf'
        with open(pdf_filename, "rb") as pdf:
            # 创建PDF资源管理器
            resource = PDFResourceManager()
            # 创建一个能在内存中读写str的对象
            rw_str = StringIO()
            # 创建一个PDF参数分析器
            laparam = LAParams()
            # 创建一个PDF设备对象
            device = TextConverter(resource, rw_str, laparams=laparam)
            # 解析PDF文件
            process_pdf(resource, device, pdf)
            # 关闭设备对象
            device.close()
            # 获取内存中写入的str
            text = rw_str.getvalue()  # type:str
            # 关闭读写对象
            rw_str.close()
            # 获取所有行
            text_list = text.split("\n")  # type:list
            print(text, text_list)

    def save_to_docx(self):
        """将数据写入docx文件：https://blog.csdn.net/cloveses/article/details/81668797"""
        pass

    def save_to_excel(self):
        """将数据保存到Excel文件:https://openpyxl.readthedocs.io/en/stable/"""
        # 创建一个Excel文件
        file = xlwt.Workbook()
        # 创建sheet
        sheet1 = file.add_sheet(u'sheet1', cell_overwrite_ok=True)
        # 设置列宽
        # 列宽xlwt中列宽的值表示方法：默认字体0的1/256为衡量单位。
        # xlwt创建时使用的默认宽度为2960，既11个字符0的宽度
        # 所以我们在设置列宽时可以用如下方法：
        # width = 256 * N    256为衡量单位，N表示N个字符宽度
        sheet1.col(0).width = 256 * 20
        sheet1.col(1).width = 256 * 50

        # 将词频数据写入第 i 行，第 j 列， i,j从0开始
        # 先写入表头标题
        sheet1.write(0, 0, "标题")  # 第1行第1列
        sheet1.write(0, 1, "名称")  # 第1行第2列
        file.save("./测试文件.xls")  # 只能保存为.xls文件，不支持保存为.xlsx

    def xml_to_str_by_re(self):
        """通过正则表达式从XML文件中提取数据"""
        with open("./result-rcn-184713_en.xml", "r", encoding="utf-8") as file:
            data = file.read()  # type: str
            # print(type(data), data)
            pat = "<.*?>"
            rep = ""
            rcn = re.search(r"<rcn>[0-9]{6}</rcn>", data).group()
            id = re.search(r"<id>.*?</id>", data).group()
            summary = re.search(r"<summary>[^<]*?</summary>", data).group()
            workPerformed = re.search(r"<workPerformed>[^<]*?</workPerformed>", data).group()
            finalResults = re.search(r"<finalResults>[^<]*?</finalResults>", data).group()
            displayCode = re.findall(r"<displayCode.*?>[^<]*?</displayCode>", data)  # type: list
            rcn = re.sub(pat, rep, rcn)
            id = re.sub(pat, rep, id)
            summary = re.sub(pat, rep, summary)
            workPerformed = re.sub(pat, rep, workPerformed)
            finalResults = re.sub(pat, rep, finalResults)
            for item in displayCode:
                displaycode = re.sub(pat, rep, item)
                print(displaycode)

            print(displayCode)


def main():
    s = Study()
    # text = s.read_from_docx()  # 读取docx文本
    # s.read_from_excel()  # 读取Excel文本
    # s.read_from_pdf()  # 读取PDF文本
    # s.save_to_excel()  # 保存到Excel文件
    s.xml_to_str_by_re()


if __name__ == '__main__':
    main()