用 Python 抓取 PDF：从链接发现到提取的表格

pip install pdfplumber pypdf beautifulsoup4

import urllib.parse

from bs4 import BeautifulSoup


def pdf_links(html, base_url):
    soup = BeautifulSoup(html, "html.parser")
    return sorted({
        urllib.parse.urljoin(base_url, a["href"])
        for a in soup.select('a[href$=".pdf"]')
    })

https://www.irs.gov/pub/irs-pdf/fw9.pdf
https://www.irs.gov/pub/irs-pdf/iw9.pdf
https://www.irs.gov/pub/irs-pdf/p1281.pdf
https://www.irs.gov/pub/irs-pdf/p5027.pdf

import urllib.request

BROWSER_UA = ("Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
              "(KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36")


def fetch_bytes(url):
    """Fetch a binary file. PDFs must arrive as bytes, never as text."""
    request = urllib.request.Request(url, headers={"User-Agent": BROWSER_UA})
    with urllib.request.urlopen(request, timeout=120) as response:
        return response.read()

import io

from pypdf import PdfReader

reader = PdfReader(io.BytesIO(raw))
print(len(reader.pages), reader.is_encrypted)

import pdfplumber

with pdfplumber.open(io.BytesIO(raw)) as pdf:
    page = pdf.pages[0]
    text = page.extract_text() or ""
    words = page.extract_words()

tables = page.extract_tables()
for index, table in enumerate(tables, 1):
    widest = max(len(row) for row in table)
    print(f"table {index}: {len(table)} rows x {widest} cols")

table 1: 4 rows x 1 cols
table 2: 2 rows x 7 cols
table 3: 1 rows x 2 cols
table 4: 2 rows x 10 cols

same pdf through the text endpoint: 235403 bytes (real file is 140815)
  pypdf reads it: failed (PdfReadError)
  pdfplumber reads it: failed (PdfminerException)

def page_count(data):
    return len(PdfReader(io.BytesIO(data)).pages)

import io
import json
import logging
import os
import urllib.parse
import urllib.request

import pdfplumber
from bs4 import BeautifulSoup
from pypdf import PdfReader

logging.getLogger("pypdf").setLevel(logging.CRITICAL)
logging.getLogger("pdfminer").setLevel(logging.CRITICAL)

UNLOCKER = "https://api.scrapeless.com/api/v2/unlocker/request"
INDEX = "https://www.irs.gov/forms-pubs/about-form-w-9"
BROWSER_UA = ("Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
              "(KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36")


def fetch_html(url):
    """Fetch a rendered HTML page as text."""
    payload = json.dumps({
        "actor": "unlocker.webunlocker",
        "input": {"url": url, "proxy_country": "US", "js_render": False},
    }).encode()
    request = urllib.request.Request(
        UNLOCKER, data=payload,
        headers={"Content-Type": "application/json",
                 "x-api-token": os.environ["SCRAPELESS_API_KEY"]},
    )
    with urllib.request.urlopen(request, timeout=120) as response:
        return json.loads(response.read().decode())["data"]


def fetch_bytes(url):
    """Fetch a binary file. PDFs must arrive as bytes, never as text."""
    request = urllib.request.Request(url, headers={"User-Agent": BROWSER_UA})
    with urllib.request.urlopen(request, timeout=120) as response:
        return response.read()


def pdf_links(html, base_url):
    soup = BeautifulSoup(html, "html.parser")
    return sorted({
        urllib.parse.urljoin(base_url, a["href"])
        for a in soup.select('a[href$=".pdf"]')
    })


def main():
    html = fetch_html(INDEX)
    links = pdf_links(html, INDEX)
    print(f"index page: {len(html)} chars")
    print(f"pdf links discovered: {len(links)}")
    for link in links:
        print(f"  {link}")

    target = next(link for link in links if link.endswith("fw9.pdf"))
    raw = fetch_bytes(target)
    print(f"downloaded: {len(raw)} bytes, header {raw[:5].decode('latin-1')!r}")

    reader = PdfReader(io.BytesIO(raw))
    print(f"pypdf: {len(reader.pages)} pages, encrypted={reader.is_encrypted}")

    with pdfplumber.open(io.BytesIO(raw)) as pdf:
        page = pdf.pages[0]
        text = page.extract_text() or ""
        print(f"pdfplumber page 1: {len(text)} chars of text")
        print(f"  first line: {text.splitlines()[0][:60]!r}")

        tables = page.extract_tables()
        print(f"tables on page 1: {len(tables)}")
        for index, table in enumerate(tables, 1):
            widest = max(len(row) for row in table)
            print(f"  table {index}: {len(table)} rows x {widest} cols")

        print(f"positioned words on page 1: {len(page.extract_words())}")

    # A PDF is binary. Prove what happens if it travels as text.
    as_text = fetch_html(target).encode("utf-8")
    print(f"same pdf through the text endpoint: {len(as_text)} bytes "
          f"(real file is {len(raw)})")

    # Open AND read a page — a lenient constructor is not proof the file is usable.
    def read_with_pypdf(data):
        return len(PdfReader(io.BytesIO(data)).pages)

    def read_with_pdfplumber(data):
        with pdfplumber.open(io.BytesIO(data)) as opened:
            return len(opened.pages)

    for name, read in (("pypdf", read_with_pypdf), ("pdfplumber", read_with_pdfplumber)):
        try:
            print(f"  {name} reads it: {read(as_text)} pages")
        except Exception as exc:
            print(f"  {name} reads it: failed ({type(exc).__name__})")


if __name__ == "__main__":
    main()

index page: 99970 chars
pdf links discovered: 4
  https://www.irs.gov/pub/irs-pdf/fw9.pdf
  https://www.irs.gov/pub/irs-pdf/iw9.pdf
  https://www.irs.gov/pub/irs-pdf/p1281.pdf
  https://www.irs.gov/pub/irs-pdf/p5027.pdf
downloaded: 140815 bytes, header '%PDF-'
pypdf: 6 pages, encrypted=False
pdfplumber page 1: 5659 chars of text
  first line: 'W-9'
tables on page 1: 4
  table 1: 4 rows x 1 cols
  table 2: 2 rows x 7 cols
  table 3: 1 rows x 2 cols
  table 4: 2 rows x 10 cols
positioned words on page 1: 933
same pdf through the text endpoint: 235403 bytes (real file is 140815)
  pypdf reads it: failed (PdfReadError)
  pdfplumber reads it: failed (PdfminerException)