1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
|
# Reading PDF Annotations
PDF 2.0 defines the following annotation types:
* Text
* Link
* FreeText
* Line
* Square
* Circle
* Polygon
* PolyLine
* Highlight
* Underline
* Squiggly
* StrikeOut
* Caret
* Stamp
* Ink
* Popup
* FileAttachment
* Sound
* Movie
* Screen
* Widget
* PrinterMark
* TrapNet
* Watermark
* 3D
* Redact
* Projection
* RichMedia
In general, annotations can be read like this:
```python
from pypdf import PdfReader
reader = PdfReader("annotated.pdf")
for page in reader.pages:
if "/Annots" in page:
for annotation in page["/Annots"]:
obj = annotation.get_object()
print({"subtype": obj["/Subtype"], "location": obj["/Rect"]})
```
Examples of reading three of the most common annotations:
## Text
```python
from pypdf import PdfReader
reader = PdfReader("example.pdf")
for page in reader.pages:
if "/Annots" in page:
for annotation in page["/Annots"]:
subtype = annotation.get_object()["/Subtype"]
if subtype == "/Text":
print(annotation.get_object()["/Contents"])
```
## Highlights
```python
from pypdf import PdfReader
reader = PdfReader("example.pdf")
for page in reader.pages:
if "/Annots" in page:
for annotation in page["/Annots"]:
subtype = annotation.get_object()["/Subtype"]
if subtype == "/Highlight":
coords = annotation.get_object()["/QuadPoints"]
x1, y1, x2, y2, x3, y3, x4, y4 = coords
```
## Attachments
```python
from pypdf import PdfReader
reader = PdfReader("example.pdf")
attachments = {}
for page in reader.pages:
if "/Annots" in page:
for annotation in page["/Annots"]:
subtype = annotation.get_object()["/Subtype"]
if subtype == "/FileAttachment":
fileobj = annotation.get_object()["/FS"]
attachments[fileobj["/F"]] = fileobj["/EF"]["/F"].get_data()
```
|
