Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update filmtipset.se.xml #1169

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Update filmtipset.se.xml #1169

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a98da9c
Update filmtipset.se.xml
vuego Nov 2, 2021
eb78d45
Update filmtipset.se.xml
vuego Feb 22, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 52 additions & 32 deletions MovingPictures/DataProviders/ScraperScripts/filmtipset.se.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,12 +14,14 @@
is for minor bug fix releases. Use it.
-->
<id>874987</id>
<version major="1" minor="6" point="9"/>
<published month="04" day="16" year="2020"/>
<version major="1" minor="8" point="0"/>
<published month="2" day="22" year="2023"/>

<!--
1.7.0 Fixed Release Date, Language, Studios, Plot Keywords, Score, Matching movies on search results page 3 and 4
These fields are used for categorization purposes. Seperate multiple
types with a pipe | character.
1.8.0 Fixed search and taglines, IMDb 8 number id, Will use Swedish release date if available or else the first release date
-->
<type>MovieDetailsFetcher</type>
<language>sv</language>
Expand All @@ -32,7 +34,7 @@
<!-- Regular Expressions -->
<set name="rx_search_results_block">
<![CDATA[
</th></tr><tr><td><a href=".*?"><strong>(.*?)</div><br/><h3>Sk.despelare/person</h3>
</th></tr><tr><td><a href=".*?"><strong>(.*?)<h3>Sk.despelare/crew</h3>
]]>
</set>
<set name="rx_search_results">
Expand All @@ -42,7 +44,7 @@
</set>
<set name="rx_imdb">
<![CDATA[
tt\d*(\d{7})"
tt0{0,2}(\d{7,8})"
]]>
</set>
<set name="rx_alternate_title_block">
Expand Down Expand Up @@ -197,7 +199,7 @@

<loop name="search_results_verified" on="search_results_block">
<parse name="movie_details" input="${search_results_verified}" regex="${rx_search_results}" />
<set name="offset" value="50"/>
<set name="offset" value="75"/>
<loop name='curr_details' on='movie_details' limit="25">
<add name="counter" value1="${count}" value2="${offset}" />
<set name="movie[${counter}].title" value="${curr_details[1]}" />
Expand Down Expand Up @@ -228,7 +230,7 @@

<loop name="search_results_verified" on="search_results_block">
<parse name="movie_details" input="${search_results_verified}" regex="${rx_search_results}" />
<set name="offset" value="50"/>
<set name="offset" value="100"/>
<loop name='curr_details' on='movie_details' limit="25">
<add name="counter" value1="${count}" value2="${offset}" />
<set name="movie[${counter}].title" value="${curr_details[1]}" />
Expand Down Expand Up @@ -305,48 +307,53 @@
</set>
<set name="rx_imdb">
<![CDATA[
tt\d*(\d{7})"
tt0{0,2}(\d{7,8})"
]]>
</set>
<set name="rx_tagline">
<![CDATA[
<h5>Tagline.</h5>[^>]+>[^\r]?(?<movieTagline>[^<]+)|Tagline[s]?:</h4>[\s\f\r]*(?<movieTagline>[^<]+)
ipc-html-content-inner-div">(.*?)</div>
]]>
</set>
<set name="rx_imdb_votes">
<![CDATA[
<span itemprop="ratingValue">(\d.\d)</span>
]]>
</set>
<set name="rx_language_block">
<![CDATA[
>Language:<\/h4>[\w\W]+>Release Date:</h4>
@type":"AggregateRating","ratingCount":(\d+),"bestRating":10,"worstRating":1,"ratingValue":(\d[.\d]*)}
]]>
</set>
<set name="rx_language">
<![CDATA[
tt_dt_dt"[\w\W]>(.*?)<\/a>
primary_language=\S+">(\w+)
]]>
</set>
<set name="rx_studios_block">
<![CDATA[
<h4 class="inline">Production Co:</h4>\s*(?<movieStudios>(?:[,]*\s*<span itemprop="creator"[^>]+>\s*)?(?:[^<]*<a[^>]+href="[^"]+"[^>]*>(?:<span[^>]+>)?[^<]+(?:</span></a></span>|</a>)))*
Production companies.+?<\/a><\/li><\/ul>
]]>
</set>
<set name="rx_studios">
<![CDATA[
<a[^>]+href="[^"]+"[^>]*>(?:<span[^>]+>)?(?<movieStudios>[^<]+)(?:</span>)?</a>
>([\w ]+)
]]>
</set>
<set name="rx_release_date">
<![CDATA[
<h4 class="inline">Release Date:</h4>\s*(?<releaseDate>\d{1,2}\s*[^\s]+\s*\d{4})
tt_dt_rdat">(\w+ \d+, \d+) \(Sweden\)
]]>
</set>
<set name="rx_release_date_releaseinfo">
<![CDATA[
Sweden[\r\n]</a></td>[\r\n]<td class="release-date-item__date" align="right">(\d+ \w+ \d+)<
]]>
</set>
<set name="rx_release_date_releaseinfo_first">
<![CDATA[
<td class="release-date-item__date" align="right">(\d+ \w+ \d+)</td>
]]>
</set>

<set name="rx_plotkeywords">
<![CDATA[
<h4[^>]+>Plot Keywords:</h4>\s*(?<moviePlotKeywords>.+?)(?:&nbsp;|<nobr>|See more|</div>)
data-item-keyword="([\w ]+?)">
]]>
</set>

Expand Down Expand Up @@ -406,24 +413,23 @@
<set name='movie.certification' value='${certification[0][0]:htmldecode}'/>

<!-- Language -->
<retrieve name="imdb_page" url="http://www.imdb.com/title/${movie.imdb_id}"/>
<parse name="language_block" input="${imdb_page}" regex='${rx_language_block}' />
<parse name="language" input="${language_block}" regex='${rx_language}' />
<retrieve name="imdb_page" url="https://www.imdb.com/title/${movie.imdb_id}/?ref_=tt_ql"/>
<parse name="language" input="${imdb_page}" regex='${rx_language}' />
<set name='movie.language' value=''/>
<loop name='currLanguage' on='language'>
<set name='movie.language' value='${movie.language}|${currLanguage[0]}'/>
</loop>

<!-- Tagline -->
<parse name="tagline" input="${imdb_page}" regex='${rx_tagline}'/>
<retrieve name="taglines_page" url="https://www.imdb.com/title/${movie.imdb_id}/taglines/"/>
<parse name="tagline" input="${taglines_page}" regex='${rx_tagline}'/>
<set name='movie.tagline' value='${tagline[0][0]:htmldecode}'/>

<!-- Score and Popularity -->
<if test="${IMDbScore}=true">
<parse name="imdb_votes" input="${imdb_page}" regex="${rx_imdb_votes}" />
<set name="movie.score" value="${imdb_votes[0][0]:htmldecode}" />
<replace name="imdb_votes_clean" input="${imdb_votes[0][0]:htmldecode}" pattern=',' with='.' />
<set name="movie.popularity" value="${imdb_votes_clean}" />
<set name="movie.score" value="${imdb_votes[0][1]:htmldecode}" />
<set name="movie.popularity" value="${imdb_votes[0][0]:htmldecode}" />
</if>

<!-- Studios -->
Expand All @@ -436,18 +442,32 @@

<!-- Release Date -->
<parse name="release_date" input="${imdb_page}" regex="${rx_release_date}" />
<!-- If IMDb.com does not have a release date, then we will use the release year -->
<!-- If IMDb.com does not have a release date, then we will try the release info page -->
<if test="${release_date[0][0]}=">
<if test="${movie.year}!=">
<set name="release_date[0][0]" value="1/1/${movie.year}" />
<retrieve name="imdb_releaseinfo" url="https://www.imdb.com/title/${movie.imdb_id}/releaseinfo"/>
<parse name="release_date" input="${imdb_releaseinfo}" regex="${rx_release_date_releaseinfo}" />

<if test="${release_date[0][0]}=">
<!-- If the details page does not have a Swedish release date, then we will use the first release date -->
<parse name="release_date" input="${imdb_releaseinfo}" regex="${rx_release_date_releaseinfo_first}" />

<if test="${release_date[0][0]}=">
<!-- If IMDb.com does not have a release date, then we will use the release year -->
<if test="${movie.year}!=">
<set name="release_date[0][0]" value="1/1/${movie.year}" />
</if>
</if>
</if>
</if>
<set name="movie.release_date" value="${release_date[0][0]}" />

<!-- Plot Keywords -->
<parse name="plotkeywords" input="${imdb_page}" regex="${rx_plotkeywords}" />
<set name="plotkeywords_clean" value="|${plotkeywords[0][0]:striptags}|" />
<replace name="movie.plotkeywords" input="${plotkeywords_clean:htmldecode}" pattern="\s*[|]+\s*" with="|" />
<retrieve name="imdb_keywords" url="https://www.imdb.com/title/${movie.imdb_id}/keywords"/>
<parse name="plotkeywords" input="${imdb_keywords}" regex="${rx_plotkeywords}" />
<set name="movie.plotkeywords" value="|" />
<loop name="currKeyword" on="plotkeywords" limit="100">
<set name="movie.plotkeywords" value="${movie.plotkeywords}${currKeyword[0]:htmldecode}|" />
</loop>

</action>

Expand Down