diff --git a/docs/index.html b/docs/index.html index 75412e3..62512d3 100644 --- a/docs/index.html +++ b/docs/index.html @@ -19,7 +19,7 @@ Python PDF parser and analyzer
Examples:
diff --git a/pdfminer/layout.py b/pdfminer/layout.py index cad790a..77ac3a2 100644 --- a/pdfminer/layout.py +++ b/pdfminer/layout.py @@ -119,6 +119,9 @@ class LayoutItem(object): self.set_bbox(bbox) return + def __repr__(self): + return ('-$ pdf2txt.py samples/naacl06-shinyama.pdf -o output.html +$ pdf2txt.py -o output.html samples/naacl06-shinyama.pdf (extract text as an HTML file whose filename is output.html) -$ pdf2txt.py -c euc-jp samples/jo.pdf -D V -o output.html +$ pdf2txt.py -c euc-jp -D V -o output.html samples/jo.pdf (extract a Japanese HTML file in vertical writing, CMap is required) -$ pdf2txt.py -P mypassword secret.pdf -o output.txt +$ pdf2txt.py -P mypassword -o output.txt secret.pdf (extract a text from an encrypted PDF file)