目录
模块:PyPDF2 和 pdfplumber
pdf信息的读取:
PyPDF2.PdfReader(filepath)读取pdf的信息
import PyPDF2 as p2
pdf1 = p2.PdfReader('易方达中小盘混合型证券投资基金2020年中期报告.pdf')
print(pdf1.getNumPages())
#获取pdf页码数量
读取页面中的文字:
pdf2 = pdfplumber.open('易方达中小盘混合型证券投资基金2020年中期报告.pdf')
for page in pdf2.pages:
print(page.extract_text())
#读取所有内容
pdf2 = pdfplumber.open('易方达中小盘混合型证券投资基金2020年中期报告.pdf')
print(pdf2.pages[0].extract_text())
#利用索引打印第一页内容
获取页面中的表格:
print(pdf2.pages[6].extract_table())
#hu获取pdf中的表格(第7页)
pdf的添加和保存
pdf = PdfFileWriter()
pdf.addpage()
'''添加页面'''
with with open(save_filepath, "wb") as out:
pdf.write(out)
'''保存pdf'''
pdf加水印(需要有一个含有水印的空白图片):
watermark = PdfFileReader(watermark_filepath)#空白水印的文件
watermark_page = watermark.getPage(0)
pdf_reader = PdfFileReader(filepath)#要添加水印的pdf
pdf_writer = PdfFileWriter()
for page_index in range(pdf_reader.getNumPages()):
current_page = pdf_reader.getPage(page_index)
# 封面页不添加水印
if page_index == 0:
new_page = current_page
else:
new_page = copy(watermark_page)
new_page.mergePage(current_page)
pdf_writer.addPage(new_page)
# 保存水印后的文件
with open(save_filepath, "wb") as out:
pdf_writer.write(out)
pdf加密与解密(encrypt(password)):
pdf3 = p2.PdfWriter()
for page in range(pdf1.getNumPages()):
pdf3.addPage(pdf1.getPage(page))
pdf3.encrypt('12345')
#设置加密密码
with open('../python&pdf&word/加密文件.pdf', "wb") as out:
pdf3.write(out)
加密后效果:
解密:
pdf3 = p2.PdfReader('加密文件.pdf')
pdf3.decrypt('12345')
pdfdecrypted = p2.PdfWriter()
for index in range(pdf3.getNumPages()):
pdfdecrypted.addPage(pdf3.getPage(index))
out2 = open('解密后文件.pdf','wb')
pdfdecrypted.write(out2)
word
模块:python-docx
基础操作:
doc_1 = docx.Document()可新建文档 add_heading('')添加标题 add_run('')添加文字 add_paragraph()添加段落
import docx
doc_1 = docx.Document()
'''新建doc'''
'''添加标题(0相当于文章的题目,默认级别是1,级别范围为0-9)'''
doc_1.add_heading('新建空白文档标题,级别为1',level = 1)
doc_1.add_heading('新建空白文档标题,级别为2',level = 2)
para1 = doc_1.add_paragraph('第一个段落')
'''添加段落'''
para1.add_run('加粗字体').bold = True
para1.add_run('普通字体')
'''增加文字同时可以添加样式'''
para2 = para1.insert_paragraph_before('在第一段文字前插入的段落')
'''在原有段落前插入段落'''
doc_1.add_page_break()
'''分页'''
para3 = doc_1.add_paragraph('第二页的段落')
'''新一页的段落'''
heading1 = doc_1.add_heading('jay chou')
heading1.alignment = docx.enum.text.WD_PARAGRAPH_ALIGNMENT.CENTER
'''添加标题并设置居中
WD_ALIGN_PARAGRAPH. LEFT:左对齐;
#WD_ALIGN_PARAGRAPH. CENTER:居中对其;
#WD_ALIGN_PARAGRAPH. RIGHT:右对齐;
#WD_ALIGN_PARAGRAPH. JUSTIFY:两端对齐;
'''
para3.paragraph_format.first_line_indent =docx.share.Cm(0.75)
para3.paragraph_format.line_spacing = 1.5
'''
设置样式:缩进0。75cm
行距1。5北
'''
text = '中国台湾华语流行歌手、' \
'音乐创作家、作曲家、作词人、' \
'制作人、杰威尔音乐公司老板之一、导演。' \
'近年涉足电影行业。周杰伦是2000年后亚洲流行乐坛最具革命性与指标' \
'性的创作歌手,有“亚洲流行天王”之称。他突破原有亚洲音乐的主题、形' \
'式,融合多元的音乐素材,创造出多变的歌曲风格,尤以融合中西式曲风的嘻哈' \
'或节奏蓝调最为著名,可说是开创华语流行音乐“中国风”的先声。周杰伦的' \
'出现打破了亚洲流行乐坛长年停滞不前的局面,为亚洲流行乐坛翻开了新的一页!'
r1 = para3.add_run(text)
#段落增加文字
r1.font.size =docx.share.Pt(10) #字号
r1.font.bold = True #加粗
r1.font.color.rgb =docx.share.RGBColor(255,0,0) #颜色
'''添加样式'''
doc_1.save('doc_1.docx')
'''保存文件'''
插入图片:
doc_1.add_picture('周杰伦.jpg',width=Inches(1.0), height=Inches(1.0))
inches需要从docx.shared导入
添加表格:
table1 = doc_1.add_table(rows=2, cols=1)
row_cells = table1.add_row().cells
#增加一行
实例(批量生成邀请函)
from openpyxl import load_workbook
from docx import Document
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
from docx.shared import RGBColor, Pt,Inches,Cm
from docx.oxml.ns import qn
path = r'D:\idea\cloud_analyse_game_sentiment\word自动化'
# 路径为Excel 文件所在的位置,可按实际情况更改
workbook = load_workbook(path + r'\excel到word.xlsx')
sheet = workbook.active #默认的WorkSheet
n = 0 #为了不遍历标题(excel的第一行)
for row in sheet.rows:
if n:
company = row[0].value
office = row[1].value
name = row[2].value
date = str(row[3].value).split()[0]
print(company, office, name, date)
doc = Document()
heading_1 = '邀 请 函'
paragraph_1 = doc.add_heading(heading_1, level=1)
# 居中对齐
paragraph_1.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
# 单独修改较大字号
for run in paragraph_1.runs:
run.font.size = Pt(17)
greeting_word_1 = '尊敬的'
greeting_word_2 = '公司'
greeting_word_3 = ',您好:'
paragraph_2 = doc.add_paragraph()
paragraph_2.add_run(greeting_word_1)
r_1 = paragraph_2.add_run(company)
r_1.font.bold = True # 加粗
r_1.font.underline = True #下划线
paragraph_2.add_run(greeting_word_2)
r_2 = paragraph_2.add_run(office)
r_2.font.bold = True # 加粗
r_2.font.underline = True #下划线
r_3 = paragraph_2.add_run(name)
r_3.font.bold = True # 加粗
r_3.font.underline = True #下划线
paragraph_2.add_run(greeting_word_3)
paragraph_3 = doc.add_paragraph()
paragraph_3.add_run('现诚挚的邀请您于2021年10月27日参加DataWhale主办的享受开源2050活动,地点在北京鸟巢,希望您届时莅临参加。')
paragraph_3.paragraph_format.first_line_indent = Cm(0.75)
paragraph_3.paragraph_format.alignment = WD_PARAGRAPH_ALIGNMENT.LEFT
paragraph_3.paragraph_format.space_after = Inches(1.0)
paragraph_3.paragraph_format.line_spacing = 1.5
paragraph_4 = doc.add_paragraph()
date_word_1 = '邀请时间:'
paragraph_4.add_run(date_word_1)
paragraph_4.alignment = WD_PARAGRAPH_ALIGNMENT.RIGHT
sign_date = "{}年{}月{}日".format(date.split('-')[0], date.split('-')[1], date.split('-')[2])
paragraph_4.add_run(sign_date).underline = True
paragraph_4.alignment = WD_PARAGRAPH_ALIGNMENT.RIGHT
#设置全文字体
for paragraph in doc.paragraphs:
for run in paragraph.runs:
run.font.color.rgb = RGBColor(0, 0, 0)
run.font.name = '楷体'
r = run._element.rPr.rFonts
r.set(qn('w:eastAsia'), '楷体')
doc.save(path + "\{}-邀请函.docx".format(name))
n = n + 1
完