Das deutsche Python-Forum

Code: Alles auswählen

searchUrlResults = []
searchNameResluts = []
def searchAnime(animeName):
    page_url = "https://anicloud.io/search?q=" + animeName.replace(" ", "+")
    html_parser = etree.HTMLParser()
    session = HTMLSession()
    resp = session.get(page_url)
    resp.html.render()
    web_page = resp.html.html
    str_io_obj = StringIO(web_page)
    dom_tree = etree.parse(str_io_obj, parser=html_parser)
    searchResults_list = dom_tree.xpath('//*[@id="searchResults"]')
    session.close()
    for a in searchResults_list:
        listChildren = a.getchildren()

        for c in listChildren:
            cChildren = c.getchildren()
            for cc in cChildren:
                episodeUrl = cc.get("href")

                if episodeUrl.startswith("/anime/stream/"):
                    if "staffel" in str(episodeUrl):
                        episodeUrl = "".join([j for j in episodeUrl if not j.isdigit()])
                        episodeUrl = episodeUrl.replace("/staffel-/episode-", "")
                    
                    if episodeUrl not in searchUrlResults:
                        searchUrlResults.append(episodeUrl)

                    episodeUrl = episodeUrl.replace("-", " ")
                    episodeUrl = episodeUrl.replace("/anime/stream/", "")
                    
                    if episodeUrl not in searchNameResluts:
                        searchNameResluts.append(episodeUrl)

Code: Alles auswählen

def getEpisodes(url):
    episodes = []
    html_parser = etree.HTMLParser()
    session = HTMLSession()
    resp = session.get(url)
    resp.html.render()
    web_page = resp.html.html
    str_io_obj = StringIO(web_page)
    dom_tree = etree.parse(str_io_obj, parser=html_parser)
    selectedElement = dom_tree.xpath('//*[@id="stream"]/ul[2]')
    session.close()

    for a in selectedElement:
        aListChildren = a.getchildren()

        for b in aListChildren:
            bListChildren = b.getchildren()

            for c in bListChildren:
                link = c.get("href")
                if isinstance(link, str):
                    episodes.append(link)

    return episodes

Code: Alles auswählen

def getEpisodes(url):
    episodes = []
    html_parser = etree.HTMLParser()
    session = HTMLSession()
    resp = session.get(url)
    resp.html.render()
    web_page = resp.html.html
    str_io_obj = StringIO(web_page)
    dom_tree = etree.parse(str_io_obj, parser=html_parser)
    selectedElement = dom_tree.xpath('//*[@id="stream"]/ul[2]')
    session.close()

    for a in selectedElement:
        aListChildren = a.getchildren()

        for b in aListChildren:
            bListChildren = b.getchildren()

            for c in bListChildren:
                link = c.get("href")
                if isinstance(link, str):
                    episodes.append(link)

    return episodes

Code: Alles auswählen

def downloadFile(fileName, downloadLink):
    print("connecting...")
    r = requests.get(downloadLink, stream=True)
    print("CONNECTED")
    with open(fileName, "wb") as f:

        total_length = int(r.headers.get('content-length'))

        for ch in progress.bar(r.iter_content(chunk_size = 255), expected_size=(total_length/255)):
            if ch:
                f.write(ch)
    print("DOWNLOAD FINISHED " + fileName)