#!/usr/bin/python3 from bs4 import BeautifulSoup from urllib.parse import urlparse import requests, os, argparse, logging class WPExport: def __init__(self, url, logger, parser): self._url = url self._logger = logger self._parser = parser def _mkdirPath(self, path_dir, logger): if not os.path.exists(path_dir): makedir = [] pathh = path_dir.split("/") for i in pathh: makedir.append(i) repath = "/".join(makedir) if not os.path.exists(repath): self._logger.debug("Dossier crée : {0}".format(repath)) try: if len(repath) > 0: os.mkdir(repath) except Exception as err: self._logger.error("Directory error : {0}".format(err)) self._logger.debug("Directory error : {0} {1} {2} {3} {4}".format(err, path_dir, repath, pathh, makedir)) exit(1) def _getScriptCss(self, js, css, logger): try: page = requests.get(url) except Exception as err: self._logger.error("Connection error : {0}".format(err)) exit(1) page_url = [] if page.status_code == 200: soup = BeautifulSoup(page.text, self._parser) if js is True: script = soup.find_all("script") for anchor in script: src = anchor.get("src", "/") if src != "/": try: u = urlparse(url) o = urlparse(src) except Exception as err: self._logger.error("parsing error : {0}".format(err)) exit(1) if o.netloc == "": o = o._replace(netloc=u.netloc) o = o._replace(scheme=u.scheme) page_url.append(o.geturl()) if css is True: link = soup.find_all("link") for anchor in link: rel = anchor.get("rel") if rel[0] == "stylesheet": href = anchor.get("href", "/") if href != "/": try: u = urlparse(url) o = urlparse(href) except Exception as err: self._logger.error("parsing error : {0}".format(err)) exit(1) if o.netloc == "": o = o._replace(netloc=u.netloc) o = o._replace(scheme=u.scheme) page_url.append(o.geturl()) return page_url def _getImg(self, webpage): page_img = [] for i in webpage: try: page = requests.get(i) except Exception as err: self._logger.error("Connection error : {0}".format(err)) exit(1) if page.status_code == 200: soup = BeautifulSoup(page.text, self._parser) img = soup.find_all("img") self._logger.info("image from page: {0} : ".format(i)) for anchor in img: src = anchor.get("src", "/") if src != "/": if src not in page_img: self._logger.info("image: {0} : ".format(src)) page_img.append(src) return page_img def _getUrlPage(self): try: page = requests.get(self._url) except Exception as err: self._logger.error("Connection error : {0}".format(err)) exit(1) page_url = [] if page.status_code == 200: soup = BeautifulSoup(page.text, self._parser) ul = soup.find_all("ul", id="listsmooth") for anchor in ul[0].find_all("a"): href = anchor.get('href', '/') if href != "#": page_url.append(href) webpage = [] for i in page_url: try: page = requests.get(i) except Exception as err: self._logger.error("Connection error : {0}".format(err)) exit(1) if page.status_code == 200: self._logger.info("page : {0}".format(i)) if i not in webpage: webpage.append(i) soup = BeautifulSoup(page.text, self._parser) class_div = pagingfirstline = soup.find_all("div", class_="pagingfirstline") if len(class_div) > 0: pagingfirstline = class_div[0].find_all("a") if len(pagingfirstline) > 1: lastpage = pagingfirstline[len(pagingfirstline)-1].get("href", "/") element_lastpage = lastpage.split("/")[len(lastpage.split("/"))-1] number_page = element_lastpage.split("-")[0].split("p")[1] number_lastpage = int(number_page) / 10 for j in range(1,int(number_lastpage)): paging = j * 10 categorie = urlparse(i).path.split("/") url_paging = "{0}/archives/p{1}-10.html".format(url, paging) if len(categorie) > 2: url_paging = "{0}/archives/{1}/p{2}-10.html".format(url, categorie[2], paging) self._logger.info(url_paging) if url_paging not in webpage: webpage.append(url_paging) page = requests.get(url_paging) if page.status_code == 200: soup = BeautifulSoup(page.text, self._parser) h2 = soup.find_all("h2") for title in h2: href = title.find_all("a")[0].get("href", "/") if href not in webpage: try: o = urlparse(href) o = o._replace(scheme="https").geturl() except Exception as err: self._logger.error("parsing error : {0}".format(err)) exit(1) webpage.append(o) return webpage def _downloadPage(self, webpage, backup_dir): for i in range(0, len(webpage)): try: o = urlparse(webpage[i]) except Exception as err: self._logger.error("parsing error : {0}".format(err)) exit(1) path_web = o.path.split("/") filePageWeb = path_web[len(path_web)-1] path_web.pop(len(path_web)-1) dir_page_web = "/".join(path_web) self._mkdirPath("{0}/{1}/{2}".format(backup_dir, o.netloc, dir_page_web)) try: r = requests.get(webpage[i]) except Exception as err: self._logger.error("Connection error : {0}".format(err)) exit(1) if r.status_code == 200: fileDownload = "{0}/{1}/index.html".format(backup_dir, o.netloc) if len(dir_page_web) > 0 and len(filePageWeb) > 0: fileDownload = "{0}/{1}{2}/{3}".format(backup_dir, o.netloc, dir_page_web, filePageWeb) self._logger.info("{0}/{1} : {2}".format(i+1, len(webpage), fileDownload)) try: open(fileDownload, "wb").write(r.content) except Exception as err: self._logger.error("file error : {0}".format(err)) exit(1) if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument("--url", help="canblog URL to be scraping", required=True) parser.add_argument("--dir", default="backup", help="backup file path") parser.add_argument("--debug", help="Verbosity", action="store_true") parser.add_argument("--logfile", help="Log file", default="") parser.add_argument("--no-css", help="No CSS", dest="css", action="store_true") parser.add_argument("--no-js", help="No JS", dest="js", action="store_true") parser.add_argument("--no-img", help="No img", dest="img", action="store_true") parser.add_argument("--no-html", help="No HTML", dest="html", action="store_true") parser.add_argument("--quiet", help="No console output", action="store_true") args = parser.parse_args() logger = logging.getLogger('web_scrap') formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') if args.quiet is False: ch = logging.StreamHandler() if args.debug is True: logger.setLevel(logging.DEBUG) ch.setLevel(logging.DEBUG) else: logger.setLevel(logging.INFO) ch.setLevel(logging.INFO) ch.setFormatter(formatter) logger.addHandler(ch) if len(args.logfile) > 0: fileHandler = logging.FileHandler(args.logfile) if args.debug is True: fileHandler.setLevel(logging.DEBUG) else: fileHandler.setLevel(logging.INFO) fileHandler.setFormatter(formatter) logger.addHandler(fileHandler) try: o = urlparse(args.url) o = o._replace(scheme="https") url = o.geturl().replace(":///", "://") except Exception as err: logger.error("parsing error : {0}".format(err)) if args.js is False: script = getScriptCss(url, True, False, logger) downloadPage(script, "{0}/{1}/{2}".format(args.dir, o.path, "dists/js"), logger) if args.css is False: css = getScriptCss(url, False, True, logger) downloadPage(css, "{0}/{1}/{2}".format(args.dir, o.path, "dists/css"), logger) if args.html is False or args.img is False: webpage = getUrlPage(url, logger) if args.html is False: downloadPage(webpage, args.dir, logger) if args.img is False: page_src = getImg(webpage, logger) downloadPage(page_src, "{0}/{1}/{2}".format(args.dir, o.path, "img"), logger)